- 83篇自然语言处理（NLP: cs.CL)
- 106篇计算机视觉(CV: cs.CV)
- 142篇机器学习(ML: cs.LG)
- 29篇人工智能(AI: cs.AI)
- 2篇信息检索(IR: cs.IR)
NLP-0-标题: IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages
作者: AI4Bharat, Jay Gala, Pranjal A. Chitale, Raghavan AK, Sumanth Doddapaneni, Varun Gumma, Aswanth Kumar, Janki Nawale, Anupama Sujatha, Ratish Puduppully, Vivek Raghavan, Pratyush Kumar, Mitesh M. Khapra, Raj Dabre, Anoop Kunchukuttan
Abstract: India has a rich linguistic landscape with languages from 4 major language families spoken by over a billion people. 22 of these languages are listed in the Constitution of India (referred to as scheduled languages) are the focus of this work. Given the linguistic diversity, high-quality and accessible Machine Translation (MT) systems are essential in a country like India. Prior to this work, there was (i) no parallel training data spanning all the 22 languages, (ii) no robust benchmarks covering all these languages and containing content relevant to India, and (iii) no existing translation models which support all the 22 scheduled languages of India. In this work, we aim to address this gap by focusing on the missing pieces required for enabling wide, easy, and open access to good machine translation systems for all 22 scheduled Indian languages. We identify four key areas of improvement: curating and creating larger training datasets, creating diverse and high-quality benchmarks, training multilingual models, and releasing models with open access. Our first contribution is the release of the Bharat Parallel Corpus Collection (BPCC), the largest publicly available parallel corpora for Indic languages. BPCC contains a total of 230M bitext pairs, of which a total of 126M were newly added, including 644K manually translated sentence pairs created as part of this work. Our second contribution is the release of the first n-way parallel benchmark covering all 22 Indian languages, featuring diverse domains, Indian-origin content, and source-original test sets. Next, we present IndicTrans2, the first model to support all 22 languages, surpassing existing models on multiple existing and new benchmarks created as a part of this work. Lastly, to promote accessibility and collaboration, we release our models and associated data with permissive licenses at this https URL.
NLP-1-标题: Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages ACL2023
作者: Shivanshu Gupta, Yoshitomo Matsubara, Ankit Chadha, Alessandro Moschitti
备注: Accepted at ACL 2023 as a long paper (Findings). Datasets are available at this https URL and this https URL
Abstract: While impressive performance has been achieved on the task of Answer Sentence Selection (AS2) for English, the same does not hold for languages that lack large labeled datasets. In this work, we propose Cross-Lingual Knowledge Distillation (CLKD) from a strong English AS2 teacher as a method to train AS2 models for low-resource languages in the tasks without the need of labeled data for the target language. To evaluate our method, we introduce 1) Xtr-WikiQA, a translation-based WikiQA dataset for 9 additional languages, and 2) TyDi-AS2, a multilingual AS2 dataset with over 70K questions spanning 8 typologically diverse languages. We conduct extensive experiments on Xtr-WikiQA and TyDi-AS2 with multiple teachers, diverse monolingual and multilingual pretrained language models (PLMs) as students, and both monolingual and multilingual training. The results demonstrate that CLKD either outperforms or rivals even supervised fine-tuning with the same amount of labeled data and a combination of machine translation and the teacher model. Our method can potentially enable stronger AS2 models for low-resource languages, while TyDi-AS2 can serve as the largest multilingual AS2 dataset for further studies in the research community.
NLP-2-标题: Landmark Attention: Random-Access Infinite Context Length for Transformer s
作者: Amirkeivan Mohtashami, Martin Jaggi
Abstract: While transformers have shown remarkable success in natural language processing, their attention mechanism’s large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or retrieval-based augmentation, have either compromised the random-access flexibility of attention (i.e., the capability to select any token in the entire context) or relied on separate mechanisms for relevant context retrieval, which may not be compatible with the model’s attention. In this paper, we present a novel approach that allows access to the complete context while retaining random-access flexibility, closely resembling running attention on the entire context. Our method uses a landmark token to represent each block of the input and trains the attention to use it for selecting relevant blocks, enabling retrieval of blocks directly through the attention mechanism instead of by relying on a separate mechanism. Our approach seamlessly integrates with specialized data structures and the system’s memory hierarchy, enabling processing of arbitrarily long context lengths. We demonstrate that our method can obtain comparable performance with Transformer-XL while significantly reducing the number of retrieved tokens in each step. Finally, we show that fine-tuning LLaMA 7B with our method successfully extends its context length capacity up to 32k tokens, allowing for inference at the context lengths of GPT-4.
NLP-3-标题: UNITE: A Unified Benchmark for Text-to-SQL Evaluation
作者: Wuwei Lan, Zhiguo Wang, Anuj Chauhan, Henghui Zhu, Alexander Li, Jiang Guo, Sheng Zhang, Chung-Wei Hang, Joseph Lilien, Yiqun Hu, Lin Pan, Mingwen Dong, Jun Wang, Jiarong Jiang, Stephen Ash, Vittorio Castelli, Patrick Ng, Bing Xiang
备注: 5 pages
Abstract: A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures. To comprehensively evaluate text-to-SQL systems, we introduce a \textbfUNIfied benchmark for \textbfText-to-SQL \textbfEvaluation (UNITE). It is composed of publicly available text-to-SQL datasets, containing natural language questions from more than 12 domains, SQL queries from more than 3.9K patterns, and 29K databases. Compared to the widely used Spider benchmark \citeyu-etal-2018-spider, we introduce \sim 120K additional examples and a threefold increase in SQL patterns, such as comparative and boolean questions. We conduct a systematic study of six state-of-the-art (SOTA) text-to-SQL parsers on our new benchmark and show that: 1) Codex performs surprisingly well on out-of-domain datasets; 2) specially designed decoding methods (e.g. constrained beam search) can improve performance for both in-domain and out-of-domain settings; 3) explicitly modeling the relationship between questions and schemas further improves the Seq2Seq models. More importantly, our benchmark presents key challenges towards compositional generalization and robustness issues – which these SOTA models cannot address well.
NLP-4-标题: Scaling Data-Constrained Language Models
作者: Niklas Muennighoff, Alexander M. Rush, Boaz Barak, Teven Le Scao, Aleksandra Piktus, Nouamane Tazi, Sampo Pyysalo, Thomas Wolf, Colin Raffel
备注: 43 pages (9 main), 35 figures, 13 tables
Abstract: The current trend of scaling language models involves increasing both parameter count and training dataset size. Extrapolating this trend suggests that training dataset size may soon be limited by the amount of text data available on the internet. Motivated by this limit, we investigate scaling language models in data-constrained regimes. Specifically, we run a large set of experiments varying the extent of data repetition and compute budget, ranging up to 900 billion training tokens and 9 billion parameter models. We find that with constrained data for a fixed compute budget, training with up to 4 epochs of repeated data yields negligible changes to loss compared to having unique data. However, with more repetition, the value of adding compute eventually decays to zero. We propose and empirically validate a scaling law for compute optimality that accounts for the decreasing value of repeated tokens and excess parameters. Finally, we experiment with approaches mitigating data scarcity, including augmenting the training dataset with code data or removing commonly used filters. Models and datasets from our 400 training runs are publicly available at this https URL.
NLP-5-标题: Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator INTERSPEECH2023
作者: Lingwei Meng, Jiawen Kang, Mingyu Cui, Haibin Wu, Xixin Wu, Helen Meng
备注: Accepted to INTERSPEECH 2023
Abstract: Multi-talker overlapped speech poses a significant challenge for speech recognition and diarization. Recent research indicated that these two tasks are inter-dependent and complementary, motivating us to explore a unified modeling method to address them in the context of overlapped speech. A recent study proposed a cost-effective method to convert a single-talker automatic speech recognition (ASR) system into a multi-talker one, by inserting a Sidecar separator into the frozen well-trained ASR model. Extending on this, we incorporate a diarization branch into the Sidecar, allowing for unified modeling of both ASR and diarization with a negligible overhead of only 768 parameters. The proposed method yields better ASR results compared to the baseline on LibriMix and LibriSpeechMix datasets. Moreover, without sophisticated customization on the diarization task, our method achieves acceptable diarization results on the two-speaker subset of CALLHOME with only a few adaptation steps.
NLP-6-标题: Neural Natural Language Processing for Long Texts: A Survey of the State-of-the-Art
作者: Dimitrios Tsirmpas, Ioannis Gkionis, Ioannis Mademlis
备注: 74 pages, 10 figures, 173 citations
Abstract: The adoption of Deep Neural Networks (DNNs) has greatly benefited Natural Language Processing (NLP) during the past decade. However, the demands of long documents analysis are quite different from those of shorter texts, with the ever increasing size of documents uploaded online rendering NLP on long documents a critical area of research. This paper surveys the current state-of-the-art in the domain, overviewing the relevant neural building blocks and subsequently focusing on two main NLP tasks: Document Classification, Summarization as well as mentioning uses in Sentiment Analysis. We detail the challenges, issues and current solutions related to long-document NLP. We also list publicly available, labelled, long-document datasets used in current research.
NLP-7-标题: Uncovering and Categorizing Social Biases in Text-to-SQL
作者: Yan Liu, Yan Gao, Zhe Su, Xiaokang Chen, Elliott Ash, Jian-Guang Lou
Abstract: Content Warning: This work contains examples that potentially implicate stereotypes, associations, and other harms that could be offensive to individuals in certain social groups. Large pre-trained language models are acknowledged to carry social biases towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and categorize social biases in Text-to-SQL models. We summarize the categories of social biases that may occur in structured data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social biases at very different rates. We show how to take advantage of our methodology to uncover and assess social biases in the downstream Text-to-SQL task. We will release our code and data.
NLP-8-标题: Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning ACL2023
作者: Genta Indra Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, Daniel Preotiuc-Pietro
备注: ACL 2023 Findings
Abstract: Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time. To do this, systems need to handle the issue of catastrophic forgetting, where the model performance drops for languages or tasks seen further in its past. In this paper, we study catastrophic forgetting, as well as methods to minimize this, in a massively multilingual continual learning framework involving up to 51 languages and covering both classification and sequence labeling tasks. We present LR ADJUST, a learning rate scheduling method that is simple, yet effective in preserving new information without strongly overwriting past knowledge. Furthermore, we show that this method is effective across multiple continual learning approaches. Finally, we provide further insights into the dynamics of catastrophic forgetting in this massively multilingual setup.
NLP-9-标题: Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models
作者: Ehsan Doostmohammadi, Tobias Norlund, Marco Kuhlmann, Richard Johansson
Abstract: Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented models commonly rely on a semantic retrieval mechanism based on the similarity between dense representations of the query chunk and potential neighbors. In this paper, we study the state-of-the-art Retro model and observe that its performance gain is better explained by surface-level similarities, such as token overlap. Inspired by this, we replace the semantic retrieval in Retro with a surface-level method based on BM25, obtaining a significant reduction in perplexity. As full BM25 retrieval can be computationally costly for large datasets, we also apply it in a re-ranking scenario, gaining part of the perplexity reduction with minimal computational overhead.
NLP-10-标题: Diversity-Aware Coherence Loss for Improving Neural Topic Models ACL2023
作者: Raymond Li, Felipe González-Pizarro, Linzi Xing, Gabriel Murray, Giuseppe Carenini
备注: 11 pages, Camera-Ready for ACL 2023 (Short Paper)
Abstract: The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic models are trained by recreating individual input documents, they do not explicitly capture the coherence between topic words on the corpus level. In this work, we propose a novel diversity-aware coherence loss that encourages the model to learn corpus-level coherence scores while maintaining a high diversity between topics. Experimental results on multiple datasets show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters.
NLP-11-标题: Abstractive Summary Generation for the Urdu Language
作者: Ali Raza, Hadia Sultan Raja, Usman Maratib
备注: 5 pages, 7 figures
Abstract: Abstractive summary generation is a challenging task that requires the model to comprehend the source text and generate a concise and coherent summary that captures the essential information. In this paper, we explore the use of an encoder/decoder approach for abstractive summary generation in the Urdu language. We employ a transformer-based model that utilizes self-attention mechanisms to encode the input text and generate a summary. Our experiments show that our model can produce summaries that are grammatically correct and semantically meaningful. We evaluate our model on a publicly available dataset and achieve state-of-the-art results in terms of Rouge scores. We also conduct a qualitative analysis of our model’s output to assess its effectiveness and limitations. Our findings suggest that the encoder/decoder approach is a promising method for abstractive summary generation in Urdu and can be extended to other languages with suitable modifications.
NLP-12-标题: Passive learning of active causal strategies in agents and language models
作者: Andrew Kyle Lampinen, Stephanie C Y Chan, Ishita Dasgupta, Andrew J Nam, Jane X Wang
Abstract: What can be learned about causality and experimentation from passive data? This question is salient given recent successes of passively-trained language models in interactive domains such as tool use. Passive learning is inherently limited. However, we show that purely passive learning can in fact allow an agent to learn generalizable strategies for determining and using causal structures, as long as the agent can intervene at test time. We formally illustrate that learning a strategy of first experimenting, then seeking goals, can allow generalization from passive learning in principle. We then show empirically that agents trained via imitation on expert data can indeed generalize at test time to infer and use causal links which are never present in the training data; these agents can also generalize experimentation strategies to novel variable sets never observed in training. We then show that strategies for causal intervention and exploitation can be generalized from passive data even in a more complex environment with high-dimensional observations, with the support of natural language explanations. Explanations can even allow passive learners to generalize out-of-distribution from perfectly-confounded training data. Finally, we show that language models, trained only on passive next-word prediction, can generalize causal intervention strategies from a few-shot prompt containing examples of experimentation, together with explanations and reasoning. These results highlight the surprising power of passive learning of active causal strategies, and may help to understand the behaviors and capabilities of language models.
NLP-13-标题: Multi-lingual and Multi-cultural Figurative Language Understanding ACL2023
作者: Anubha Kabra, Emmy Liu, Simran Khanuja, Alham Fikri Aji, Genta Indra Winata, Samuel Cahyawijaya, Anuoluwapo Aremu, Perez Ogayo, Graham Neubig
备注: ACL 2023 Findings
Abstract: Figurative language permeates human communication, but at the same time is relatively understudied in NLP. Datasets have been created in English to accelerate progress towards measuring and improving figurative language processing in language models (LMs). However, the use of figurative language is an expression of our cultural and societal experiences, making it difficult for these phrases to be universally applicable. In this work, we create a figurative language inference dataset, \datasetname, for seven diverse languages associated with a variety of cultures: Hindi, Indonesian, Javanese, Kannada, Sundanese, Swahili and Yoruba. Our dataset reveals that each language relies on cultural and regional concepts for figurative expressions, with the highest overlap between languages originating from the same region. We assess multilingual LMs’ abilities to interpret figurative language in zero-shot and few-shot settings. All languages exhibit a significant deficiency compared to English, with variations in performance reflecting the availability of pre-training and fine-tuning data, emphasizing the need for LMs to be exposed to a broader range of linguistic and cultural variation during training.
NLP-14-标题: Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis ACL2023
作者: Xuming Hu, Zhijiang Guo, Zhiyang Teng, Irwin King, Philip S. Yu
备注: Accepted to ACL 2023
Abstract: Multimodal relation extraction (MRE) is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair. Existing retrieval-augmented approaches mainly focused on modeling the retrieved textual knowledge, but this may not be able to accurately identify complex relations. To improve the prediction, this research proposes to retrieve textual and visual evidence based on the object, sentence, and whole image. We further develop a novel approach to synthesize the object-level, image-level, and sentence-level information for better reasoning between the same and different modalities. Extensive experiments and analyses show that the proposed method is able to effectively select and compare evidence across modalities and significantly outperforms state-of-the-art models.
NLP-15-标题: Feature Collapse
作者: Thomas Laurent, James H. von Brecht, Xavier Bresson
Abstract: We formalize and study a phenomenon called feature collapse that makes precise the intuitive idea that entities playing a similar role in a learning task receive similar representations. As feature collapse requires a notion of task, we leverage a simple but prototypical NLP task to study it. We start by showing experimentally that feature collapse goes hand in hand with generalization. We then prove that, in the large sample limit, distinct words that play identical roles in this NLP task receive identical local feature representations in a neural network. This analysis reveals the crucial role that normalization mechanisms, such as LayerNorm, play in feature collapse and in generalization.
NLP-16-标题: Training Data Extraction From Pre-trained Language Models: A Survey ACL2023
作者: Shotaro Ishihara
备注: TrustNLP workshop at ACL 2023
Abstract: As the deployment of pre-trained language models (PLMs) expands, pressing security concerns have arisen regarding the potential for malicious extraction of training data, posing a threat to data privacy. This study is the first to provide a comprehensive survey of training data extraction from PLMs. Our review covers more than 100 key papers in fields such as natural language processing and security. First, preliminary knowledge is recapped and a taxonomy of various definitions of memorization is presented. The approaches for attack and defense are then systemized. Furthermore, the empirical findings of several quantitative studies are highlighted. Finally, future research directions based on this review are suggested.
NLP-17-标题: Revisiting Non-Autoregressive Translation at Scale ACL2023
作者: Zhihao Wang, Longyue Wang, Jinsong Su, Junfeng Yao, Zhaopeng Tu
备注: 13 pages, Findings of ACL 2023
Abstract: In real-world systems, scaling has been critical for improving the translation quality in autoregressive translation (AT), which however has not been well studied for non-autoregressive translation (NAT). In this work, we bridge the gap by systematically studying the impact of scaling on NAT behaviors. Extensive experiments on six WMT benchmarks over two advanced NAT models show that scaling can alleviate the commonly-cited weaknesses of NAT models, resulting in better translation performance. To reduce the side-effect of scaling on decoding speed, we empirically investigate the impact of NAT encoder and decoder on the translation performance. Experimental results on the large-scale WMT20 En-De show that the asymmetric architecture (e.g. bigger encoder and smaller decoder) can achieve comparable performance with the scaling model, while maintaining the superiority of decoding speed with standard NAT models. To this end, we establish a new benchmark by validating scaled NAT models on the scaled dataset, which can be regarded as a strong baseline for future works. We release code, models and system outputs at this https URL.
NLP-18-标题: Language Models Implement Simple Word2Vec-style Vector Arithmetic
作者: Jack Merullo, Carsten Eickhoff, Ellie Pavlick
Abstract: A primary criticism towards language models (LMs) is their inscrutability. This paper presents evidence that, despite their size and complexity, LMs sometimes exploit a computational mechanism familiar from traditional word embeddings: the use of simple vector arithmetic in order to encode abstract relations (e.g., Poland:Warsaw::China:Beijing). We investigate a range of language model sizes (from 124M parameters to 176B parameters) in an in-context learning setting, and find that for a variety of tasks (involving capital cities, upper-casing, and past-tensing), a key part of the mechanism reduces to a simple linear update applied by the feedforward networks. We further show that this mechanism is specific to tasks that require retrieval from pretraining memory, rather than retrieval from local context. Our results contribute to a growing body of work on the mechanistic interpretability of LLMs, and offer reason to be optimistic that, despite the massive and non-linear nature of the models, the strategies they ultimately use to solve tasks can sometimes reduce to familiar and even intuitive algorithms.
NLP-19-标题: Give Me More Details: Improving Fact-Checking with Latent Retrieval ACL2023
作者: Xuming Hu, Zhijiang Guo, Guanyu Wu, Lijie Wen, Philip S. Yu
备注: Accepted to ACL 2023, 15 pages
Abstract: Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods ignore the challenges of collecting evidence and may not provide sufficient information to verify real-world claims. Aiming at building a better fact-checking system, we propose to incorporate full text from source documents as evidence and introduce two enriched datasets. The first one is a multilingual dataset, while the second one is monolingual (English). We further develop a latent variable model to jointly extract evidence sentences from documents and perform claim verification. Experiments indicate that including source documents can provide sufficient contextual clues even when gold evidence sentences are not annotated. The proposed system is able to achieve significant improvements upon best-reported models under different settings.
NLP-20-标题: VioLA: Unified Codec Language Models for Speech Recognition Synthesis and Translation
作者: Tianrui Wang, Long Zhou, Ziqiang Zhang, Yu Wu, Shujie Liu, Yashesh Gaur, Zhuo Chen, Jinyu Li, Furu Wei
备注: Working in progress
Abstract: Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text, such as speech-to-text, text-to-text, text-to-speech, and speech-to-speech tasks, as a conditional codec language model task via multi-task learning framework. To accomplish this, we first convert all the speech utterances to discrete tokens (similar to the textual data) using an offline neural codec encoder. In such a way, all these tasks are converted to token-based sequence conversion problems, which can be naturally handled with one conditional language model. We further integrate task IDs (TID) and language IDs (LID) into the proposed model to enhance the modeling capability of handling different languages and tasks. Experimental results demonstrate that the proposed VioLA model can support both single-modal and cross-modal tasks well, and the decoder-only model achieves a comparable and even better performance than the strong baselines.
NLP-21-标题: Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue System ACL2023
作者: Shimin Li, Xiaotian Zhang, Yanjun Zheng, Linyang Li, Xipeng Qiu
备注: Accepted to Findings of ACL 2023
Abstract: Dialogue data in real scenarios tend to be sparsely available, rendering data-starved end-to-end dialogue systems trained inadequately. We discover that data utilization efficiency in low-resource scenarios can be enhanced by mining alignment information uncertain utterance and deterministic dialogue state. Therefore, we innovatively implement dual learning in task-oriented dialogues to exploit the correlation of heterogeneous data. In addition, the one-to-one duality is converted into a multijugate duality to reduce the influence of spurious correlations in dual training for generalization. Without introducing additional parameters, our method could be implemented in arbitrary networks. Extensive empirical analyses demonstrate that our proposed method improves the effectiveness of end-to-end task-oriented dialogue systems under multiple benchmarks and obtains state-of-the-art results in low-resource scenarios.
NLP-22-标题: ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
作者: Zijia Zhao, Longteng Guo, Tongtian Yue, Sihan Chen, Shuai Shao, Xinxin Zhu, Zehuan Yuan, Jing Liu
Abstract: Building general-purpose models that can perceive diverse real-world modalities and solve various tasks is an appealing target in artificial intelligence. In this paper, we present ChatBridge, a novel multimodal language model that leverages the expressive capabilities of language as the catalyst to bridge the gap between various modalities. We show that only language-paired two-modality data is sufficient to connect all modalities. ChatBridge leverages recent large language models (LLM) and extends their zero-shot capabilities to incorporate diverse multimodal inputs. ChatBridge undergoes a two-stage training. The first stage aligns each modality with language, which brings emergent multimodal correlation and collaboration abilities. The second stage instruction-finetunes ChatBridge to align it with user intent with our newly proposed multimodal instruction tuning dataset, named MULTIS, which covers a wide range of 16 multimodal tasks of text, image, video, and audio modalities. We show strong quantitative and qualitative results on zero-shot multimodal tasks covering text, image, video, and audio modalities. All codes, data, and models of ChatBridge will be open-sourced.
NLP-23-标题: End-to-End Simultaneous Speech Translation with Differentiable Segmentation ACL2023
作者: Shaolei Zhang, Yang Feng
备注: Accepted at ACL 2023 findings
Abstract: End-to-end simultaneous speech translation (SimulST) outputs translation while receiving the streaming speech inputs (a.k.a. streaming speech translation), and hence needs to segment the speech inputs and then translate based on the current received speech. However, segmenting the speech inputs at unfavorable moments can disrupt the acoustic integrity and adversely affect the performance of the translation model. Therefore, learning to segment the speech inputs at those moments that are beneficial for the translation model to produce high-quality translation is the key to SimulST. Existing SimulST methods, either using the fixed-length segmentation or external segmentation model, always separate segmentation from the underlying translation model, where the gap results in segmentation outcomes that are not necessarily beneficial for the translation process. In this paper, we propose Differentiable Segmentation (DiSeg) for SimulST to directly learn segmentation from the underlying translation model. DiSeg turns hard segmentation into differentiable through the proposed expectation training, enabling it to be jointly trained with the translation model and thereby learn translation-beneficial segmentation. Experimental results demonstrate that DiSeg achieves state-of-the-art performance and exhibits superior segmentation capability.
NLP-24-标题: Fake News Detection and Behavioral Analysis: Case of COVID-19
作者: Chih-Yuan Li, Navya Martin Kollapally, Soon Ae Chun, James Geller
备注: 27 pages, 11 figures, 13 tables
Abstract: While the world has been combating COVID-19 for over three years, an ongoing “Infodemic” due to the spread of fake news regarding the pandemic has also been a global issue. The existence of the fake news impact different aspect of our daily lives, including politics, public health, economic activities, etc. Readers could mistake fake news for real news, and consequently have less access to authentic information. This phenomenon will likely cause confusion of citizens and conflicts in society. Currently, there are major challenges in fake news research. It is challenging to accurately identify fake news data in social media posts. In-time human identification is infeasible as the amount of the fake news data is overwhelming. Besides, topics discussed in fake news are hard to identify due to their similarity to real news. The goal of this paper is to identify fake news on social media to help stop the spread. We present Deep Learning approaches and an ensemble approach for fake news detection. Our detection models achieved higher accuracy than previous studies. The ensemble approach further improved the detection performance. We discovered feature differences between fake news and real news items. When we added them into the sentence embeddings, we found that they affected the model performance. We applied a hybrid method and built models for recognizing topics from posts. We found half of the identified topics were overlapping in fake news and real news, which could increase confusion in the population.
NLP-25-标题: What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns ACL
作者: Anne Lauscher, Debora Nozza, Archie Crowley, Ehm Miltersen, Dirk Hovy
备注: Accepted to ACL
Abstract: As 3rd-person pronoun usage shifts to include novel forms, e.g., neopronouns, we need more research on identity-inclusive NLP. Exclusion is particularly harmful in one of the most popular NLP applications, machine translation (MT). Wrong pronoun translations can discriminate against marginalized groups, e.g., non-binary individuals (Dev et al., 2021). In this ``reality check’', we study how three commercial MT systems translate 3rd-person pronouns. Concretely, we compare the translations of gendered vs. gender-neutral pronouns from English to five other languages (Danish, Farsi, French, German, Italian), and vice versa, from Danish to English. Our error analysis shows that the presence of a gender-neutral pronoun often leads to grammatical and semantic translation errors. Similarly, gender neutrality is often not preserved. By surveying the opinions of affected native speakers from diverse languages, we provide recommendations to address the issue in future MT research.
NLP-26-标题: UFO: Unified Fact Obtaining for Commonsense Question Answering IJCNN2023
作者: Zhifeng Li, Yifan Fan, Bowei Zou, Yu Hong
备注: IJCNN 2023
Abstract: Leveraging external knowledge to enhance the reasoning ability is crucial for commonsense question answering. However, the existing knowledge bases heavily rely on manual annotation which unavoidably causes deficiency in coverage of world-wide commonsense knowledge. Accordingly, the knowledge bases fail to be flexible enough to support the reasoning over diverse questions. Recently, large-scale language models (LLMs) have dramatically improved the intelligence in capturing and leveraging knowledge, which opens up a new way to address the issue of eliciting knowledge from language models. We propose a Unified Facts Obtaining (UFO) approach. UFO turns LLMs into knowledge sources and produces relevant facts (knowledge statements) for the given question. We first develop a unified prompt consisting of demonstrations that cover different aspects of commonsense and different question styles. On this basis, we instruct the LLMs to generate question-related supporting facts for various commonsense questions via prompting. After facts generation, we apply a dense retrieval-based fact selection strategy to choose the best-matched fact. This kind of facts will be fed into the answer inference model along with the question. Notably, due to the design of unified prompts, UFO can support reasoning in various commonsense aspects (including general commonsense, scientific commonsense, and social commonsense). Extensive experiments on CommonsenseQA 2.0, OpenBookQA, QASC, and Social IQA benchmarks show that UFO significantly improves the performance of the inference model and outperforms manually constructed knowledge sources.
NLP-27-标题: Efficient Document Embeddings via Self- Contrastive Bregman Divergence Learning ACL2023
作者: Daniel Saggau, Mina Rezaei, Bernd Bisch, Ilias Chalkidis
备注: 5 pages, short paper at Findings of ACL 2023
Abstract: Learning quality document embeddings is a fundamental problem in natural language processing (NLP), information retrieval (IR), recommendation systems, and search engines. Despite recent advances in the development of transformer-based models that produce sentence embeddings with self-contrastive learning, the encoding of long documents (Ks of words) is still challenging with respect to both efficiency and quality considerations. Therefore, we train Longfomer-based document encoders using a state-of-the-art unsupervised contrastive learning method (SimCSE). Further on, we complement the baseline method – siamese neural network – with additional convex neural networks based on functional Bregman divergence aiming to enhance the quality of the output document representations. We show that overall the combination of a self-contrastive siamese network and our proposed neural Bregman network outperforms the baselines in two linear classification settings on three long document topic classification tasks from the legal and biomedical domains.
NLP-28-标题: NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts ACL2023
作者: Yue Zhang, Bo Zhang, Haochen Jiang, Zhenghua Li, Chen Li, Fei Huang, Min Zhang
备注: Accepted by ACL 2023 (Findings, long paper)
Abstract: We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains. Previous CGEC research primarily focuses on correcting texts from a single domain, especially learner essays. To broaden the target domain, we annotate multiple references for 12,500 sentences from three native domains, i.e., social media, scientific writing, and examination. We provide solid benchmark results for NaSGEC by employing cutting-edge CGEC models and different training data. We further perform detailed analyses of the connections and gaps between our domains from both empirical and statistical views. We hope this work can inspire future studies on an important but under-explored direction–cross-domain GEC.
NLP-29-标题: Do You Hear The People Sing? Key Point Analysis via Iterative Clustering and Abstractive Summarisation ACL2023
作者: Hao Li, Viktor Schlegel, Riza Batista-Navarro, Goran Nenadic
备注: Accepted by ACL 2023 Main Conference
Abstract: Argument summarisation is a promising but currently under-explored field. Recent work has aimed to provide textual summaries in the form of concise and salient short texts, i.e., key points (KPs), in a task known as Key Point Analysis (KPA). One of the main challenges in KPA is finding high-quality key point candidates from dozens of arguments even in a small corpus. Furthermore, evaluating key points is crucial in ensuring that the automatically generated summaries are useful. Although automatic methods for evaluating summarisation have considerably advanced over the years, they mainly focus on sentence-level comparison, making it difficult to measure the quality of a summary (a set of KPs) as a whole. Aggravating this problem is the fact that human evaluation is costly and unreproducible. To address the above issues, we propose a two-step abstractive summarisation framework based on neural topic modelling with an iterative clustering procedure, to generate key points which are aligned with how humans identify key points. Our experiments show that our framework advances the state of the art in KPA, with performance improvement of up to 14 (absolute) percentage points, in terms of both ROUGE and our own proposed evaluation metrics. Furthermore, we evaluate the generated summaries using a novel set-based evaluation toolkit. Our quantitative analysis demonstrates the effectiveness of our proposed evaluation metrics in assessing the quality of generated KPs. Human evaluation further demonstrates the advantages of our approach and validates that our proposed evaluation metric is more consistent with human judgment than ROUGE scores.
NLP-30-标题: Visually grounded few-shot word acquisition with fewer shots INTERSPEECH2023
作者: Leanne Nortje, Benjamin van Niekerk, Herman Kamper
备注: Accepted at Interspeech 2023
Abstract: We propose a visually grounded speech model that acquires new words and their visual depictions from just a few word-image example pairs. Given a set of test images and a spoken query, we ask the model which image depicts the query word. Previous work has simplified this problem by either using an artificial setting with digit word-image pairs or by using a large number of examples per class. We propose an approach that can work on natural word-image pairs but with less examples, i.e. fewer shots. Our approach involves using the given word-image example pairs to mine new unsupervised word-image training pairs from large collections of unlabelled speech and images. Additionally, we use a word-to-image attention mechanism to determine word-image similarity. With this new model, we achieve better performance with fewer shots than any existing approach.
NLP-31-标题: BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering ACL2023
作者: Jie He, Simon Chi Lok U, Víctor Gutiérrez-Basulto, Jeff Z. Pan
备注: Accepted by ACL2023
Abstract: Unsupervised commonsense reasoning (UCR) is becoming increasingly popular as the construction of commonsense reasoning datasets is expensive, and they are inevitably limited in their scope. A popular approach to UCR is to fine-tune language models with external knowledge (e.g., knowledge graphs), but this usually requires a large number of training examples. In this paper, we propose to transform the downstream multiple choice question answering task into a simpler binary classification task by ranking all candidate answers according to their reasonableness. To this end, for training the model, we convert the knowledge graph triples into reasonable and unreasonable texts. Extensive experimental results show the effectiveness of our approach on various multiple choice question answering benchmarks. Furthermore, compared with existing UCR approaches using KGs, ours is less data hungry. Our code is available at this https URL.
NLP-32-标题: Emergence of a phonological bias in ChatGPT
作者: Juan Manuel Toro
备注: 11 pages, 1 figure
Abstract: Current large language models, such as OpenAI’s ChatGPT, have captured the public’s attention because how remarkable they are in the use of language. Here, I demonstrate that ChatGPT displays phonological biases that are a hallmark of human language processing. More concretely, just like humans, ChatGPT has a consonant bias. That is, the chatbot has a tendency to use consonants over vowels to identify words. This is observed across languages that differ in their relative distribution of consonants and vowels such as English and Spanish. Despite the differences in how current artificial intelligence language models are trained to process linguistic stimuli and how human infants acquire language, such training seems to be enough for the emergence of a phonological bias in ChatGPT
NLP-33-标题: Reliable identification of selection mechanisms in language change
作者: Juan Guerrero Montero, Andres Karjus, Kenny Smith, Richard A. Blythe
Abstract: Language change is a cultural evolutionary process in which variants of linguistic variables change in frequency through processes analogous to mutation, selection and genetic drift. In this work, we apply a recently-introduced method to corpus data to quantify the strength of selection in specific instances of historical language change. We first demonstrate, in the context of English irregular verbs, that this method is more reliable and interpretable than similar methods that have previously been applied. We further extend this study to demonstrate that a bias towards phonological simplicity overrides that favouring grammatical simplicity when these are in conflict. Finally, with reference to Spanish spelling reforms, we show that the method can also detect points in time at which selection strengths change, a feature that is generically expected for socially-motivated language change. Together, these results indicate how hypotheses for mechanisms of language change can be tested quantitatively using historical corpus data.
NLP-34-标题: MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched Contextualization
作者: Shivam Sharma, Ramaneswaram S, Udit Arora, Md. Shad Akhtar, Tanmoy Chakraborty
备注: 9 pages main + 1 ethics + 3 pages ref. + 4 pages app (Total: 17 pages)
Abstract: Memes are a powerful tool for communication over social media. Their affinity for evolving across politics, history, and sociocultural phenomena makes them an ideal communication vehicle. To comprehend the subtle message conveyed within a meme, one must understand the background that facilitates its holistic assimilation. Besides digital archiving of memes and their metadata by a few websites like this http URL, currently, there is no efficient way to deduce a meme’s context dynamically. In this work, we propose a novel task, MEMEX - given a meme and a related document, the aim is to mine the context that succinctly explains the background of the meme. At first, we develop MCC (Meme Context Corpus), a novel dataset for MEMEX. Further, to benchmark MCC, we propose MIME (MultImodal Meme Explainer), a multimodal neural framework that uses common sense enriched meme representation and a layered approach to capture the cross-modal semantic dependencies between the meme and the context. MIME surpasses several unimodal and multimodal systems and yields an absolute improvement of ~ 4% F1-score over the best baseline. Lastly, we conduct detailed analyses of MIME’s performance, highlighting the aspects that could lead to optimal modeling of cross-modal contextual associations.
NLP-35-标题: Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?
作者: Seyed Mahed Mousavi, Simone Caldarella, Giuseppe Riccardi
Abstract: Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of dialogue sessions. Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e.g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events. In this paper, we study the task of response generation in LDs. We evaluate whether general-purpose Pre-trained Language Models (PLM) are appropriate for this purpose. We fine-tune two PLMs, GePpeTto (GPT-2) and iT5, using a dataset of LDs. We experiment with different representations of the personal knowledge extracted from LDs for grounded response generation, including the graph representation of the mentioned events and participants. We evaluate the performance of the models via automatic metrics and the contribution of the knowledge via the Integrated Gradients technique. We categorize the natural language generation errors via human evaluations of contextualization, appropriateness and engagement of the user.
NLP-36-标题: MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation ACL2023
作者: Sebastian Vincent, Robert Flynn, Carolina Scarton
备注: Accepted to Findings at ACL2023
Abstract: Efficient utilisation of both intra- and extra-textual context remains one of the critical gaps between machine and human translation. Existing research has primarily focused on providing individual, well-defined types of context in translation, such as the surrounding text or discrete external variables like the speaker’s gender. This work introduces MTCue, a novel neural machine translation (NMT) framework that interprets all context (including discrete variables) as text. MTCue learns an abstract representation of context, enabling transferability across different data settings and leveraging similar attributes in low-resource scenarios. With a focus on a dialogue domain with access to document and metadata context, we extensively evaluate MTCue in four language pairs in both translation directions. Our framework demonstrates significant improvements in translation quality over a parameter-matched non-contextual baseline, as measured by BLEU (+0.88) and Comet (+1.58). Moreover, MTCue significantly outperforms a “tagging” baseline at translating English text. Analysis reveals that the context encoder of MTCue learns a representation space that organises context based on specific attributes, such as formality, enabling effective zero-shot control. Pre-training on context embeddings also improves MTCue’s few-shot performance compared to the “tagging” baseline. Finally, an ablation study conducted on model components and contextual variables further supports the robustness of MTCue for context-based NMT.
NLP-37-标题: Collective Knowledge Graph Completion with Mutual Knowledge Distillation NEURIPS2022
作者: Weihang Zhang, Ovidiu Serban, Jiahao Sun, Yi-ke Guo
备注: Accepted at ENLSP-II workshop at NeurIPS 2022
Abstract: Knowledge graph completion (KGC), the task of predicting missing information based on the existing relational data inside a knowledge graph (KG), has drawn significant attention in recent years. However, the predictive power of KGC methods is often limited by the completeness of the existing knowledge graphs from different sources and languages. In monolingual and multilingual settings, KGs are potentially complementary to each other. In this paper, we study the problem of multi-KG completion, where we focus on maximizing the collective knowledge from different KGs to alleviate the incompleteness of individual KGs. Specifically, we propose a novel method called CKGC-CKD that uses relation-aware graph convolutional network encoder models on both individual KGs and a large fused KG in which seed alignments between KGs are regarded as edges for message propagation. An additional mutual knowledge distillation mechanism is also employed to maximize the knowledge transfer between the models of “global” fused KG and the “local” individual KGs. Experimental results on multilingual datasets have shown that our method outperforms all state-of-the-art models in the KGC task.
NLP-38-标题: Private Meeting Summarization Without Performance Loss SIGIR23
作者: Seolhwa Lee, Anders Søgaard
备注: SIGIR23 Main conference
Abstract: Meeting summarization has an enormous business potential, but in addition to being a hard problem, roll-out is challenged by privacy concerns. We explore the problem of meeting summarization under differential privacy constraints and find, to our surprise, that while differential privacy leads to slightly lower performance on in-sample data, differential privacy improves performance when evaluated on unseen meeting types. Since meeting summarization systems will encounter a great variety of meeting types in practical employment scenarios, this observation makes safe meeting summarization seem much more feasible. We perform extensive error analysis and identify potential risks in meeting summarization under differential privacy, including a faithfulness analysis.
NLP-39-标题: CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset
作者: Hanchong Zhang, Jieyu Li, Lu Chen, Ruisheng Cao, Yunyan Zhang, Yu Huang, Yefeng Zheng, Kai Yu
Abstract: The cross-domain text-to-SQL task aims to build a system that can parse user questions into SQL on complete unseen databases, and the single-domain text-to-SQL task evaluates the performance on identical databases. Both of these setups confront unavoidable difficulties in real-world applications. To this end, we introduce the cross-schema text-to-SQL task, where the databases of evaluation data are different from that in the training data but come from the same domain. Furthermore, we present CSS, a large-scale CrosS-Schema Chinese text-to-SQL dataset, to carry on corresponding studies. CSS originally consisted of 4,340 question/SQL pairs across 2 databases. In order to generalize models to different medical systems, we extend CSS and create 19 new databases along with 29,280 corresponding dataset examples. Moreover, CSS is also a large corpus for single-domain Chinese text-to-SQL studies. We present the data collection approach and a series of analyses of the data statistics. To show the potential and usefulness of CSS, benchmarking baselines have been conducted and reported. Our dataset is publicly available at \urlthis https URL.
NLP-40-标题: LFTK: Handcrafted Features in Computational Linguistics ACL2023
作者: Bruce W. Lee, Jason Hyung-Jong Lee
备注: BEA @ ACL 2023
Abstract: Past research has identified a rich set of handcrafted linguistic features that can potentially assist various tasks. However, their extensive number makes it difficult to effectively select and utilize existing handcrafted features. Coupled with the problem of inconsistent implementation across research works, there has been no categorization scheme or generally-accepted feature names. This creates unwanted confusion. Also, most existing handcrafted feature extraction libraries are not open-source or not actively maintained. As a result, a researcher often has to build such an extraction system from the ground up. We collect and categorize more than 220 popular handcrafted features grounded on past literature. Then, we conduct a correlation analysis study on several task-specific datasets and report the potential use cases of each feature. Lastly, we devise a multilingual handcrafted linguistic feature extraction system in a systematically expandable manner. We open-source our system for public access to a rich set of pre-implemented handcrafted features. Our system is coined LFTK and is the largest of its kind. Find it at this http URL.
NLP-41-标题: Linguistic Properties of Truthful Response ACL2023
作者: Bruce W. Lee, Benedict Florance Arockiaraj, Helen Jin
备注: TrustNLP @ ACL 2023
Abstract: We investigate the phenomenon of an LLM’s untruthful response using a large set of 220 handcrafted linguistic features. We focus on GPT-3 models and find that the linguistic profiles of responses are similar across model sizes. That is, how varying-sized LLMs respond to given prompts stays similar on the linguistic properties level. We expand upon this finding by training support vector machines that rely only upon the stylistic components of model responses to classify the truthfulness of statements. Though the dataset size limits our current findings, we present promising evidence that truthfulness detection is possible without evaluating the content itself.
NLP-42-标题: Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation
作者: Yandan Zheng, Anran Hao, Anh Tuan Luu
Abstract: Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples. Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data.
NLP-43-标题: Extracting Text Representations for Terms and Phrases in Technical Domains ACL2023
作者: Francesco Fusco, Diego Antognini
备注: Accepted at ACL 2023 (industry). 10 pages, 3 figures, 5 tables
Abstract: Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple applications ranging from ranking results in search to summarization. Common approaches to create dense representations include training domain-specific embeddings with self-supervised setups or using sentence encoder models trained over similarity tasks. In contrast to static embeddings, sentence encoders do not suffer from the out-of-vocabulary (OOV) problem, but impose significant computational costs. In this paper, we propose a fully unsupervised approach to text encoding that consists of training small character-based models with the objective of reconstructing large pre-trained embedding matrices. Models trained with this approach can not only match the quality of sentence encoders in technical domains, but are 5 times smaller and up to 10 times faster, even on high-end GPUs.
NLP-44-标题: Sequential Integrated Gradients: a simple but effective method for explaining language models ACL2023
作者: Joseph Enguehard
备注: Accepted at ACL 2023 Findings
Abstract: Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these methods produce a path for each word of a sentence simultaneously, which could lead to creating sentences from interpolated words either having no clear meaning, or having a significantly different meaning compared to the original sentence. In order to keep the meaning of these sentences as close as possible to the original one, we propose Sequential Integrated Gradients (SIG), which computes the importance of each word in a sentence by keeping fixed every other words, only creating interpolations between the baseline and the word of interest. Moreover, inspired by the training procedure of several language models, we also propose to replace the baseline token “pad” with the trained token “mask”. While being a simple improvement over the original IG method, we show on various models and datasets that SIG proves to be a very effective method for explaining language models.
NLP-45-标题: Self-contradictory Hallucinations of Large Language Models: Evaluation Detection and Mitigation
作者: Niels Mündler, Jingxuan He, Slobodan Jenko, Martin Vechev
Abstract: Large language models (large LMs) are susceptible to producing text with hallucinated content. Self-contradiction, where the LM generates two contradictory sentences within the same context, is an important form of hallucination. In this work, we present a comprehensive analysis on self-contradiction for state-of-the-art, instruction-tuned LMs, including evaluation, detection, and mitigation. To effectively trigger self-contradictions, we design a framework that constrains LMs to generate appropriate sentence pairs. Our evaluation on these sentence pairs reveals that self-contradictions occur frequently across different LMs for both famous and lesser-known topics. Next, we prompt the LMs to detect self-contradictions. Our results indicate that ChatGPT and GPT-4 are able to accurately identify self-contradictions, while Vicuna-13B struggles to do so. For example, with our best prompting method, ChatGPT achieves 91.0% precision and 80.5% recall on the sentence pairs generated by itself. To automatically mitigate self-contradictions, we develop an iterative algorithm that prompts the LMs to remove the detected self-contradictions from the generated text. Our algorithm successfully revises the text such that self-contradictions are significantly reduced, while maintaining its fluency and informativeness. Importantly, our entire pipeline of triggering, detecting, and mitigating self-contradictions is applicable to black-box LMs and does not require any external grounded knowledge.
NLP-46-标题: Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages
作者: Yash Madhani, Mitesh M. Khapra, Anoop Kunchukuttan
Abstract: We create publicly available language identification (LID) datasets and models in all 22 Indian languages listed in the Indian constitution in both native-script and romanized text. First, we create Bhasha-Abhijnaanam, a language identification test set for native-script as well as romanized text which spans all 22 Indic languages. We also train IndicLID, a language identifier for all the above-mentioned languages in both native and romanized script. For native-script text, it has better language coverage than existing LIDs and is competitive or better than other LIDs. IndicLID is the first LID for romanized text in Indian languages. Two major challenges for romanized text LID are the lack of training data and low-LID performance when languages are similar. We provide simple and effective solutions to these problems. In general, there has been limited work on romanized text in any language, and our findings are relevant to other languages that need romanized language identification. Our models are publicly available at this https URL under open-source licenses. Our training and test sets are also publicly available at this https URL under open-source licenses.
NLP-47-标题: Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformer s
作者: Sotiris Anagnostidis, Dario Pavllo, Luca Biggio, Lorenzo Noci, Aurelien Lucchi, Thomas Hoffmann
Abstract: Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens in the sequence, thus incurring a quadratic cost. In this study, we present a novel approach that dynamically prunes contextual information while preserving the model’s expressiveness, resulting in reduced memory and computational requirements during inference. Our method employs a learnable mechanism that determines which uninformative tokens can be dropped from the context at any point across the generation process. By doing so, our approach not only addresses performance concerns but also enhances interpretability, providing valuable insight into the model’s decision-making process. Our technique can be applied to existing pre-trained models through a straightforward fine-tuning process, and the pruning strength can be specified by a sparsity parameter. Notably, our empirical findings demonstrate that we can effectively prune up to 80% of the context without significant performance degradation on downstream tasks, offering a valuable tool for mitigating inference costs. Our reference implementation achieves up to 2\times increase in inference throughput and even greater memory savings.
NLP-48-标题: MERGE: Fast Private Text Generation
作者: Zi Liang, Pinghui Wang, Ruofei Zhang, Nuo Xu, Shuo Zhang
Abstract: Recent years have seen increasing concerns about the private inference of NLP services and Transformer models. However, existing two-party privacy-preserving methods solely consider NLU scenarios, while the private inference of text generation such as translation, dialogue, and code completion remains unsolved. Besides, while migrated to NLG models, existing privacy-preserving methods perform poorly in terms of inference speed, and suffer from the convergence problem during the training stage. To address these issues, we propose MERGE, a fast private text generation framework for Transformer-based language models. Specifically, MERGE reuse the output hidden state as the word embedding to bypass the embedding computation, and reorganize the linear operations in the Transformer module to accelerate the forward procedure. Based on these two optimizations, extensive experiments show that MERGE can achieve a 26.5x speedup under the sequence length 512, and reduce 80% communication bytes, with an up to 10x speedup to existing state-of-art models.
NLP-49-标题: Svarah: Evaluating English ASR Systems on Indian Accents
作者: Tahir Javed, Sakshi Joshi, Vignesh Nagarajan, Sai Sundaresan, Janki Nawale, Abhigyan Raman, Kaushal Bhogale, Pratyush Kumar, Mitesh M. Khapra
Abstract: India is the second largest English-speaking country in the world with a speaker base of roughly 130 million. Thus, it is imperative that automatic speech recognition (ASR) systems for English should be evaluated on Indian accents. Unfortunately, Indian speakers find a very poor representation in existing English ASR benchmarks such as LibriSpeech, Switchboard, Speech Accent Archive, etc. In this work, we address this gap by creating Svarah, a benchmark that contains 9.6 hours of transcribed English audio from 117 speakers across 65 geographic locations throughout India, resulting in a diverse range of accents. Svarah comprises both read speech and spontaneous conversational data, covering various domains, such as history, culture, tourism, etc., ensuring a diverse vocabulary. We evaluate 6 open source ASR models and 2 commercial ASR systems on Svarah and show that there is clear scope for improvement on Indian accents. Svarah as well as all our code will be publicly available.
NLP-50-标题: Healing Unsafe Dialogue Responses with Weak Supervision Signals
作者: Zi Liang, Pinghui Wang, Ruofei Zhang, Shuo Zhang, Xiaofan Ye Yi Huang, Junlan Feng
Abstract: Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus. Some methods are proposed to address the above issue by detecting and replacing unsafe training examples in a pipeline style. Though effective, they suffer from a high annotation cost and adapt poorly to unseen scenarios as well as adversarial attacks. Besides, the neglect of providing safe responses (e.g. simply replacing with templates) will cause the information-missing problem of dialogues. To address these issues, we propose an unsupervised pseudo-label sampling method, TEMP, that can automatically assign potential safe responses. Specifically, our TEMP method groups responses into several clusters and samples multiple labels with an adaptively sharpened sampling strategy, inspired by the observation that unsafe samples in the clusters are usually few and distribute in the tail. Extensive experiments in chitchat and task-oriented dialogues show that our TEMP outperforms state-of-the-art models with weak supervision signals and obtains comparable results under unsupervised learning settings.
NLP-51-标题: UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation ACL-2023
作者: Zhiming Mao, Huimin Wang, Yiming Du, Kam-fai Wong
备注: ACL-2023 Short Paper
Abstract: Prior study has shown that pretrained language models (PLM) can boost the performance of text-based recommendation. In contrast to previous works that either use PLM to encode user history as a whole input text, or impose an additional aggregation network to fuse multi-turn history representations, we propose a unified local- and global-attention Transformer encoder to better model two-level contexts of user history. Moreover, conditioned on user history encoded by Transformer encoders, our framework leverages Transformer decoders to estimate the language perplexity of candidate text items, which can serve as a straightforward yet significant contrastive signal for user-item text matching. Based on this, our framework, UniTRec, unifies the contrastive objectives of discriminative matching scores and candidate text perplexity to jointly enhance text-based recommendation. Extensive evaluation shows that UniTRec delivers SOTA performance on three text-based recommendation tasks. Code is available at this https URL.
NLP-52-标题: Learn to Not Link: Exploring NIL Prediction in Entity Linking ACL
作者: Fangwei Zhu, Jifan Yu, Hailong Jin, Juanzi Li, Lei Hou, Zhifang Sui
备注: ACL Findings 2023
Abstract: Entity linking models have achieved significant success via utilizing pretrained language models to capture semantic features. However, the NIL prediction problem, which aims to identify mentions without a corresponding entity in the knowledge base, has received insufficient attention. We categorize mentions linking to NIL into Missing Entity and Non-Entity Phrase, and propose an entity linking dataset NEL that focuses on the NIL prediction problem. NEL takes ambiguous entities as seeds, collects relevant mention context in the Wikipedia corpus, and ensures the presence of mentions linking to NIL by human annotation and entity masking. We conduct a series of experiments with the widely used bi-encoder and cross-encoder entity linking models, results show that both types of NIL mentions in training data have a significant influence on the accuracy of NIL prediction. Our code and dataset can be accessed at this https URL
NLP-53-标题: Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data
作者: Aryan Patil, Varad Patwardhan, Abhishek Phaltankar, Gauri Takawane, Raviraj Joshi
备注: Accepted at IEEE 8th International Conference for Convergence in Technology
Abstract: The term “Code Mixed” refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount of adaptation as time goes on. It is critical to detect foreign elements in a language and process them correctly, as a considerable number of individuals are using code-mixed languages that could not be comprehended by understanding one of those languages. In this work, we focus on low-resource Hindi-English code-mixed language and enhancing the performance of different code-mixed natural language processing tasks such as sentiment analysis, emotion recognition, and hate speech identification. We perform a comparative analysis of different Transformer-based language Models pre-trained using unsupervised approaches. We have included the code-mixed models like HingBERT, HingRoBERTa, HingRoBERTa-Mixed, mBERT, and non-code-mixed models like AlBERT, BERT, and RoBERTa for comparative analysis of code-mixed Hindi-English downstream tasks. We report state-of-the-art results on respective datasets using HingBERT-based models which are specifically pre-trained on real code-mixed text. Our HingBERT-based models provide significant improvements thus highlighting the poor performance of vanilla BERT models on code-mixed text.
NLP-54-标题: Towards Higher Pareto Frontier in Multilingual Machine Translation ACL2023
作者: Yichong Huang, Xiaocheng Feng, Xinwei Geng, Baohang Li, Bing Qin
备注: Accepted by ACL2023
Abstract: Multilingual neural machine translation has witnessed remarkable progress in recent years. However, the long-tailed distribution of multilingual corpora poses a challenge of Pareto optimization, i.e., optimizing for some languages may come at the cost of degrading the performance of others. Existing balancing training strategies are equivalent to a series of Pareto optimal solutions, which trade off on a Pareto frontier. In this work, we propose a new training framework, Pareto Mutual Distillation (Pareto-MD), towards pushing the Pareto frontier outwards rather than making trade-offs. Specifically, Pareto-MD collaboratively trains two Pareto optimal solutions that favor different languages and allows them to learn from the strengths of each other via knowledge distillation. Furthermore, we introduce a novel strategy to enable stronger communication between Pareto optimal solutions and broaden the applicability of our approach. Experimental results on the widely-used WMT and TED datasets show that our method significantly pushes the Pareto frontier and outperforms baselines by up to +2.46 BLEU.
NLP-55-标题: The False Promise of Imitating Proprietary LLMs
作者: Arnav Gudibande, Eric Wallace, Charlie Snell, Xinyang Geng, Hao Liu, Pieter Abbeel, Sergey Levine, Dawn Song
Abstract: An emerging method to cheaply improve a weaker language model is to finetune it on outputs from a stronger model, such as a proprietary system like ChatGPT (e.g., Alpaca, Self-Instruct, and others). This approach looks to cheaply imitate the proprietary model’s capabilities using a weaker open-source model. In this work, we critically analyze this approach. We first finetune a series of LMs that imitate ChatGPT using varying base model sizes (1.5B–13B), data sources, and imitation data amounts (0.3M–150M tokens). We then evaluate the models using crowd raters and canonical NLP benchmarks. Initially, we were surprised by the output quality of our imitation models – they appear far better at following instructions, and crowd workers rate their outputs as competitive with ChatGPT. However, when conducting more targeted automatic evaluations, we find that imitation models close little to none of the gap from the base LM to ChatGPT on tasks that are not heavily supported in the imitation data. We show that these performance discrepancies may slip past human raters because imitation models are adept at mimicking ChatGPT’s style but not its factuality. Overall, we conclude that model imitation is a false promise: there exists a substantial capabilities gap between open and closed LMs that, with current methods, can only be bridged using an unwieldy amount of imitation data or by using more capable base LMs. In turn, we argue that the highest leverage action for improving open-source models is to tackle the difficult challenge of developing better base LMs, rather than taking the shortcut of imitating proprietary systems.
NLP-56-标题: Zero-shot Approach to Overcome Perturbation Sensitivity of Prompt s
作者: Mohna Chakraborty, Adithya Kulkarni, Qi Li
Abstract: Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task. Specifically, these methods utilize few-shot learning settings to fine-tune the sentiment classification model using manual or automatically generated prompts. However, the performance of these methods is sensitive to the perturbations of the utilized prompts. Furthermore, these methods depend on a few labeled instances for automatic prompt generation and prompt ranking. This study aims to find high-quality prompts for the given task in a zero-shot setting. Given a base prompt, our proposed approach automatically generates multiple prompts similar to the base prompt employing positional, reasoning, and paraphrasing techniques and then ranks the prompts using a novel metric. We empirically demonstrate that the top-ranked prompts are high-quality and significantly outperform the base prompt and the prompts generated using few-shot learning for the binary sentence-level sentiment classification task.
NLP-57-标题: RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
作者: Lei Shu, Liangchen Luo, Jayakumar Hoskere, Yun Zhu, Canoee Liu, Simon Tong, Jindong Chen, Lei Meng
Abstract: Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities in long-form text generation tasks expressed through natural language instructions. However, user expectations for long-form text rewriting is high, and unintended rewrites (‘‘hallucinations’’) produced by the model can negatively impact its overall performance. Existing evaluation benchmarks primarily focus on limited rewriting styles and sentence-level rewriting rather than long-form open-ended rewriting.We introduce OpenRewriteEval, a novel benchmark that covers a wide variety of rewriting types expressed through natural language instructions. It is specifically designed to facilitate the evaluation of open-ended rewriting of long-form texts. In addition, we propose a strong baseline model, RewriteLM, an instruction-tuned large language model for long-form text rewriting. We develop new strategies that facilitate the generation of diverse instructions and preference data with minimal human intervention. We conduct empirical experiments and demonstrate that our model outperforms the current state-of-the-art LLMs in text rewriting. Specifically, it excels in preserving the essential content and meaning of the source text, minimizing the generation of ‘‘hallucinated’’ content, while showcasing the ability to generate rewrites with diverse wording and structures.
NLP-58-标题: Perturbation-based Self-supervised Attention for Attention Bias in Text Classification
作者: Huawen Feng, Zhenxi Lin, Qianli Ma
Abstract: In text classification, the traditional attention mechanisms usually focus too much on frequent words, and need extensive labeled data in order to learn. This paper proposes a perturbation-based self-supervised attention approach to guide attention learning without any annotation overhead. Specifically, we add as much noise as possible to all the words in the sentence without changing their semantics and predictions. We hypothesize that words that tolerate more noise are less significant, and we can use this information to refine the attention distribution. Experimental results on three text classification tasks show that our approach can significantly improve the performance of current attention-based models, and is more effective than existing self-supervised methods. We also provide a visualization analysis to verify the effectiveness of our approach.
NLP-59-标题: Revisiting non-English Text Simplification: A Unified Multilingual Benchmark ACL2023
作者: Michael J. Ryan, Tarek Naous, Wei Xu
备注: Accepted to ACL 2023 main conference
Abstract: Recent advancements in high-quality, large-scale English resources have pushed the frontier of English Automatic Text Simplification (ATS) research. However, less work has been done on multilingual text simplification due to the lack of a diverse evaluation benchmark that covers complex-simple sentence pairs in many languages. This paper introduces the MultiSim benchmark, a collection of 27 resources in 12 distinct languages containing over 1.7 million complex-simple sentence pairs. This benchmark will encourage research in developing more effective multilingual text simplification models and evaluation metrics. Our experiments using MultiSim with pre-trained multilingual language models reveal exciting performance improvements from multilingual training in non-English settings. We observe strong performance from Russian in zero-shot cross-lingual transfer to low-resource languages. We further show that few-shot prompting with BLOOM-176b achieves comparable quality to reference simplifications outperforming fine-tuned models in most languages. We validate these findings through human evaluation.
NLP-60-标题: Enhancing Grammatical Error Correction Systems with Explanations ACL2023
作者: Yuejiao Fei, Leyang Cui, Sen Yang, Wai Lam, Zhenzhong Lan, Shuming Shi
备注: 9 pages, 7 figures, accepted to the main conference of ACL 2023
Abstract: Grammatical error correction systems improve written communication by detecting and correcting language mistakes. To help language learners better understand why the GEC system makes a certain correction, the causes of errors (evidence words) and the corresponding error types are two key factors. To enhance GEC systems with explanations, we introduce EXPECT, a large dataset annotated with evidence words and grammatical error types. We propose several baselines and anlysis to understand this task. Furthermore, human evaluation verifies our explainable GEC system’s explanations can assist second-language learners in determining whether to accept a correction suggestion and in understanding the associated grammar rule.
NLP-61-标题: Book GPT : A General Framework for Book Recommendation Empowered by Large Language Model
作者: Aakas Zhiyuli, Yanfang Chen, Xuan Zhang, Xun Liang
备注: Under Review
Abstract: With the continuous development and change exhibited by large language model (LLM) technology, represented by generative pretrained transformers (GPTs), many classic scenarios in various fields have re-emerged with new opportunities. This paper takes ChatGPT as the modeling object, incorporates LLM technology into the typical book resource understanding and recommendation scenario for the first time, and puts it into practice. By building a ChatGPT-like book recommendation system (BookGPT) framework based on ChatGPT, this paper attempts to apply ChatGPT to recommendation modeling for three typical tasks, book rating recommendation, user rating recommendation, and book summary recommendation, and explores the feasibility of LLM technology in book recommendation scenarios. At the same time, based on different evaluation schemes for book recommendation tasks and the existing classic recommendation models, this paper discusses the advantages and disadvantages of the BookGPT in book recommendation scenarios and analyzes the opportunities and improvement directions for subsequent LLMs in these scenarios.
NLP-62-标题: Mixture-of-Expert Conformer for Streaming Multilingual ASR INTERSPEECH2023
作者: Ke Hu, Bo Li, Tara N. Sainath, Yu Zhang, Francoise Beaufays
备注: Accepted to Interspeech 2023
Abstract: End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingual Conformer incorporating mixture-of-expert (MoE) layers that learn to only activate a subset of parameters in training and inference. The MoE layer consists of a softmax gate which chooses the best two experts among many in forward propagation. The proposed MoE layer offers efficient inference by activating a fixed number of parameters as the number of experts increases. We evaluate the proposed model on a set of 12 languages, and achieve an average 11.9% relative improvement in WER over the baseline. Compared to an adapter model using ground truth information, our MoE model achieves similar WER and activates similar number of parameters but without any language information. We further show around 3% relative WER improvement by multilingual shallow fusion.
NLP-63-标题: ConvGQR: Generative Query Reformulation for Conversational Search ACL2023
作者: Fengran Mo, Kelong Mao, Yutao Zhu, Yihong Wu, Kaiyu Huang, Jian-Yun Nie
备注: Accepted at ACL 2023
Abstract: In conversational search, the user’s real search intent for the current turn is dependent on the previous conversation history. It is challenging to determine a good search query from the whole conversation context. To avoid the expensive re-training of the query encoder, most existing methods try to learn a rewriting model to de-contextualize the current query by mimicking the manual query rewriting. However, manually rewritten queries are not always the best search queries. Training a rewriting model on them would limit the model’s ability to produce good search queries. Another useful hint is the potential answer to the question. In this paper, we propose ConvGQR, a new framework to reformulate conversational queries based on generative pre-trained language models (PLMs), one for query rewriting and another for generating potential answers. By combining both, ConvGQR can produce better search queries. In addition, to relate query reformulation to retrieval performance, we propose a knowledge infusion mechanism to optimize both query reformulation and retrieval. Extensive experiments on four conversational search datasets demonstrate the effectiveness of ConvGQR.
NLP-64-标题: Morphological Inflection: A Reality Check ACL2023
作者: Jordan Kodner, Sarah Payne, Salam Khalifa, Zoey Liu
备注: To appear at ACL 2023
Abstract: Morphological inflection is a popular task in sub-word NLP with both practical and cognitive applications. For years now, state-of-the-art systems have reported high, but also highly variable, performance across data sets and languages. We investigate the causes of this high performance and high variability; we find several aspects of data set creation and evaluation which systematically inflate performance and obfuscate differences between languages. To improve generalizability and reliability of results, we propose new data sampling and evaluation strategies that better reflect likely use-cases. Using these new strategies, we make new observations on the generalization abilities of current inflection systems.
NLP-65-标题: Revisiting Sentence Union Generation as a Testbed for Text Consolidation ACL2023
作者: Eran Hirsch, Valentina Pyatkin, Ruben Wolhandler, Avi Caciularu, Asi Shefer, Ido Dagan
备注: Findings of the Association for Computational Linguistics (ACL 2023)
Abstract: Tasks involving text generation based on multiple input texts, such as multi-document summarization, long-form question answering and contemporary dialogue applications, challenge models for their ability to properly consolidate partly-overlapping multi-text information. However, these tasks entangle the consolidation phase with the often subjective and ill-defined content selection requirement, impeding proper assessment of models’ consolidation capabilities. In this paper, we suggest revisiting the sentence union generation task as an effective well-defined testbed for assessing text consolidation capabilities, decoupling the consolidation challenge from subjective content selection. To support research on this task, we present refined annotation methodology and tools for crowdsourcing sentence union, create the largest union dataset to date and provide an analysis of its rich coverage of various consolidation aspects. We then propose a comprehensive evaluation protocol for union generation, including both human and automatic evaluation. Finally, as baselines, we evaluate state-of-the-art language models on the task, along with a detailed analysis of their capacity to address multi-text consolidation challenges and their limitations.
NLP-66-标题: Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models ACL23
作者: Pengcheng Jiang, Shivam Agarwal, Bowen Jin, Xuan Wang, Jimeng Sun, Jiawei Han
备注: 18 pages, 11 figures, 8 tables. Accepted by ACL 23’ Findings
Abstract: The mission of open knowledge graph (KG) completion is to draw new findings from known facts. Existing works that augment KG completion require either (1) factual triples to enlarge the graph reasoning space or (2) manually designed prompts to extract knowledge from a pre-trained language model (PLM), exhibiting limited performance and requiring expensive efforts from experts. To this end, we propose TAGREAL that automatically generates quality query prompts and retrieves support information from large text corpora to probe knowledge from PLM for KG completion. The results show that TAGREAL achieves state-of-the-art performance on two benchmark datasets. We find that TAGREAL has superb performance even with limited training data, outperforming existing embedding-based, graph-based, and PLM-based methods.
NLP-67-标题: Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
作者: Haonan Duan, Adam Dziedzic, Nicolas Papernot, Franziska Boenisch
Abstract: Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective membership inference attack against the data used to prompt LLMs. To address this vulnerability, one could forego prompting and resort to fine-tuning LLMs with known algorithms for private gradient descent. However, this comes at the expense of the practicality and efficiency offered by prompting. Therefore, we propose to privately learn to prompt. We first show that soft prompts can be obtained privately through gradient descent on downstream data. However, this is not the case for discrete prompts. Thus, we orchestrate a noisy vote among an ensemble of LLMs presented with different prompts, i.e., a flock of stochastic parrots. The vote privately transfers the flock’s knowledge into a single public prompt. We show that LLMs prompted with our private algorithms closely match the non-private baselines. For example, using GPT3 as the base model, we achieve a downstream accuracy of 92.7% on the sst2 dataset with ( \epsilon=0.147, \delta=10^-6 )-differential privacy vs. 95.2% for the non-private baseline. Through our experiments, we also show that our prompt-based approach is easily deployed with existing commercial APIs.
NLP-68-标题: How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks ACL2023
作者: Salijona Dyrmishi, Salah Ghamizi, Maxime Cordy
备注: ACL 2023
Abstract: Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks – malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However, evaluations of these attacks ignore the property of imperceptibility or study it under limited settings. This entails that adversarial perturbations would not pass any human quality gate and do not represent real threats to human-checked NLP systems. To bypass this limitation and enable proper assessment (and later, improvement) of NLP model robustness, we have surveyed 378 human participants about the perceptibility of text adversarial examples produced by state-of-the-art methods. Our results underline that existing text attacks are impractical in real-world scenarios where humans are involved. This contrasts with previous smaller-scale human studies, which reported overly optimistic conclusions regarding attack success. Through our work, we hope to position human perceptibility as a first-class success criterion for text attacks, and provide guidance for research to build effective attack algorithms and, in turn, design appropriate defence mechanisms.
NLP-69-标题: Balancing Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer
作者: Debarati Das, David Ma, Dongyeop Kang
Abstract: Text style transfer is an exciting task within the field of natural language generation that is often plagued by the need for high-quality paired datasets. Furthermore, training a model for multi-attribute text style transfer requires datasets with sufficient support across all combinations of the considered stylistic attributes, adding to the challenges of training a style transfer model. This paper explores the impact of training data input diversity on the quality of the generated text from the multi-style transfer model. We construct a pseudo-parallel dataset by devising heuristics to adjust the style distribution in the training samples. We balance our training dataset using marginal and joint distributions to train our style transfer models. We observe that a balanced dataset produces more effective control effects over multiple styles than an imbalanced or skewed one. Through quantitative analysis, we explore the impact of multiple style distributions in training data on style-transferred output. These findings will better inform the design of style-transfer datasets.
NLP-70-标题: Refocusing Is Key to Transfer Learning
作者: Baifeng Shi, Siyu Gai, Trevor Darrell, Xin Wang
备注: Code is available at this https URL
Abstract: Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we emphasize the importance of refocusing the attention in transfer learning. We introduce Top-Down Attention Steering (TOAST), a novel transfer learning algorithm that keeps the pre-trained backbone frozen, while selecting the task-relevant elements in the output and feeding them back to the model to steer its attention to the task-specific features. By refocusing the attention only, TOAST achieves state-of-the-art results on a number of transfer learning benchmarks, while having a small portion of tunable parameters. Compared to fully fine-tuning, LoRA, and prompt tuning, TOAST substantially improves performance across a range of fine-grained visual classification datasets (e.g., 81.1% -> 86.2% on FGVC). TOAST also outperforms the fully fine-tuned Alpaca model on instruction-following language generation. Code is available at this https URL.
NLP-71-标题: Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation
作者: Yuan Yang, Siheng Xiong, Ali Payani, Ehsan Shareghi, Faramarz Fekri
Abstract: Translating natural language sentences to first-order logic (NL-FOL translation) is a longstanding challenge in the NLP and formal logic literature. This paper introduces LogicLLaMA, a LLaMA-7B model fine-tuned for NL-FOL translation using LoRA on a single GPU. LogicLLaMA is capable of directly translating natural language into FOL rules, which outperforms GPT-3.5. LogicLLaMA is also equipped to correct FOL rules predicted by GPT-3.5, and can achieve similar performance as GPT-4 with a fraction of the cost. This correction ability was achieved by a novel supervised fine-tuning (SFT) + reinforcement learning with human feedback (RLHF) framework, which initially trains on synthetically perturbed NL-FOL pairs to encourage chain-of-thought reasoning and then fine-tunes with RLHF on GPT-3.5 outputs using a FOL verifier as the reward model. To train LogicLLaMA, we present MALLS (large language \textbfM odel gener \textbfA ted N \textbfL -FO \textbfL pair \textbfS ), a dataset of 34K high-quality and diverse sentence-level NL-FOL pairs collected from GPT-4. The dataset was created by implementing a pipeline that prompts GPT-4 for pairs, and dynamically adjusts the prompts to ensure the collection of pairs with rich and diverse contexts at different levels of complexity, and verifies the validity of the generated FOL rules. Codes, weights, and data are available at \hrefthis https URL\small \textthis https URL .
NLP-72-标题: Automated Refugee Case Analysis: An NLP Pipeline for Supporting Legal Practitioners ACL
作者: Claire Barale, Michael Rovatsos, Nehal Bhuta
备注: 9 pages, preprint of long paper accepted to Findings of the Annual Meeting of the Association for Computational Linguistics (ACL) 2023
Abstract: In this paper, we introduce an end-to-end pipeline for retrieving, processing, and extracting targeted information from legal cases. We investigate an under-studied legal domain with a case study on refugee law in Canada. Searching case law for past similar cases is a key part of legal work for both lawyers and judges, the potential end-users of our prototype. While traditional named-entity recognition labels such as dates provide meaningful information in legal work, we propose to extend existing models and retrieve a total of 19 useful categories of items from refugee cases. After creating a novel data set of cases, we perform information extraction based on state-of-the-art neural named-entity recognition (NER). We test different architectures including two transformer models, using contextual and non-contextual embeddings, and compare general purpose versus domain-specific pre-training. The results demonstrate that models pre-trained on legal data perform best despite their smaller size, suggesting that domain matching had a larger effect than network architecture. We achieve a F1 score above 90% on five of the targeted categories and over 80% on four further categories.
NLP-73-标题: Large Language Models are Few-Shot Health Learners
作者: Xin Liu, Daniel McDuff, Geza Kovacs, Isaac Galatzer-Levy, Jacob Sunshine, Jiening Zhan, Ming-Zher Poh, Shun Liao, Paolo Di Achille, Shwetak Patel
Abstract: Large language models (LLMs) can capture rich representations of concepts that are useful for real-world tasks. However, language alone is limited. While existing LLMs excel at text-based inferences, health applications require that models be grounded in numerical data (e.g., vital signs, laboratory values in clinical domains; steps, movement in the wellness domain) that is not easily or readily expressed as text in existing training corpus. We demonstrate that with only few-shot tuning, a large language model is capable of grounding various physiological and behavioral time-series data and making meaningful inferences on numerous health tasks for both clinical and wellness contexts. Using data from wearable and medical sensor recordings, we evaluate these capabilities on the tasks of cardiac signal analysis, physical activity recognition, metabolic calculation (e.g., calories burned), and estimation of stress reports and mental health screeners.
NLP-74-标题: Exploring Automatically Perturbed Natural Language Explanations in Relation Extraction
作者: Wanyun Cui, Xingran Chen
Abstract: Previous research has demonstrated that natural language explanations provide valuable inductive biases that guide models, thereby improving the generalization ability and data efficiency. In this paper, we undertake a systematic examination of the effectiveness of these explanations. Remarkably, we find that corrupted explanations with diminished inductive biases can achieve competitive or superior performance compared to the original explanations. Our findings furnish novel insights into the characteristics of natural language explanations in the following ways: (1) the impact of explanations varies across different training styles and datasets, with previously believed improvements primarily observed in frozen language models. (2) While previous research has attributed the effect of explanations solely to their inductive biases, our study shows that the effect persists even when the explanations are completely corrupted. We propose that the main effect is due to the provision of additional context space. (3) Utilizing the proposed automatic perturbed context, we were able to attain comparable results to annotated explanations, but with a significant increase in computational efficiency, 20-30 times faster.
NLP-75-标题: Free Lunch for Efficient Textual Commonsense Integration in Language Models
作者: Wanyun Cui, Xingran Chen
Abstract: Recent years have witnessed the emergence of textual commonsense knowledge bases, aimed at providing more nuanced and context-rich knowledge. The integration of external commonsense into language models has been shown to be a key enabler in advancing the state-of-the-art for a wide range of NLP tasks. However, incorporating textual commonsense descriptions is computationally expensive, as compared to encoding conventional symbolic knowledge. In this paper, we propose a method to improve its efficiency without modifying the model. We group training samples with similar commonsense descriptions into a single batch, thus reusing the encoded description across multiple samples. One key observation is that the upper bound of batch partitioning can be reduced to the classic \it graph k-cut problem. Consequently, we propose a spectral clustering-based algorithm to solve this problem. Extensive experiments illustrate that the proposed batch partitioning approach effectively reduces the computational cost while preserving performance. The efficiency improvement is more pronounced on larger datasets and on devices with more memory capacity, attesting to its practical utility for large-scale applications.
NLP-76-标题: The Larger They Are the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python ACL2023
作者: Antonio Valerio Miceli-Barone, Fazl Barez, Ioannis Konstas, Shay B. Cohen
备注: 17 pages, 5 figure, ACL 2023
Abstract: Large Language Models (LLMs) have successfully been applied to code generation tasks, raising the question of how well these models understand programming. Typical programming languages have invariances and equivariances in their semantics that human programmers intuitively understand and exploit, such as the (near) invariance to the renaming of identifiers. We show that LLMs not only fail to properly generate correct Python code when default function names are swapped, but some of them even become more confident in their incorrect predictions as the model size increases, an instance of the recently discovered phenomenon of Inverse Scaling, which runs contrary to the commonly observed trend of increasing prediction quality with increasing model size. Our findings indicate that, despite their astonishing typical-case performance, LLMs still lack a deep, abstract understanding of the content they manipulate, making them unsuitable for tasks that statistically deviate from their training data, and that mere scaling is not enough to achieve such capability.
NLP-77-标题: Deriving Language Models from Masked Language Models ACL2023
作者: Lucas Torroba Hennigen, Yoon Kim
备注: Accepted to ACL 2023
Abstract: Masked language models (MLM) do not explicitly define a distribution over language, i.e., they are not language models per se. However, recent work has implicitly treated them as such for the purposes of generation and scoring. This paper studies methods for deriving explicit joint distributions from MLMs, focusing on distributions over two tokens, which makes it possible to calculate exact distributional properties. We find that an approach based on identifying joints whose conditionals are closest to those of the MLM works well and outperforms existing Markov random field-based approaches. We further find that this derived model’s conditionals can even occasionally outperform the original MLM’s conditionals.
NLP-78-标题: Large Language Models for User Interest Journeys
作者: Konstantina Christakopoulou, Alberto Lalama, Cj Adams, Iris Qu, Yifat Amir, Samer Chucri, Pierce Vollucci, Fabio Soldo, Dina Bseiso, Sarah Scodel, Lucas Dixon, Ed H. Chi, Minmin Chen
Abstract: Large language models (LLMs) have shown impressive capabilities in natural language understanding and generation. Their potential for deeper user understanding and improved personalized user experience on recommendation platforms is, however, largely untapped. This paper aims to address this gap. Recommender systems today capture users’ interests through encoding their historical activities on the platforms. The generated user representations are hard to examine or interpret. On the other hand, if we were to ask people about interests they pursue in their life, they might talk about their hobbies, like I just started learning the ukulele, or their relaxation routines, e.g., I like to watch Saturday Night Live, or I want to plant a vertical garden. We argue, and demonstrate through extensive experiments, that LLMs as foundation models can reason through user activities, and describe their interests in nuanced and interesting ways, similar to how a human would. We define interest journeys as the persistent and overarching user interests, in other words, the non-transient ones. These are the interests that we believe will benefit most from the nuanced and personalized descriptions. We introduce a framework in which we first perform personalized extraction of interest journeys, and then summarize the extracted journeys via LLMs, using techniques like few-shot prompting, prompt-tuning and fine-tuning. Together, our results in prompting LLMs to name extracted user journeys in a large-scale industrial platform demonstrate great potential of these models in providing deeper, more interpretable, and controllable user understanding. We believe LLM powered user understanding can be a stepping stone to entirely new user experiences on recommendation platforms that are journey-aware, assistive, and enabling frictionless conversation down the line.
NLP-79-标题: Prompt NER: Prompt ing For Named Entity Recognition
作者: Dhananjay Ashok, Zachary C. Lipton
Abstract: In a surprising turn, Large Language Models (LLMs) together with a growing arsenal of prompt-based heuristics now offer powerful off-the-shelf approaches providing few-shot solutions to myriad classic NLP problems. However, despite promising early results, these LLM-based few-shot methods remain far from the state of the art in Named Entity Recognition (NER), where prevailing methods include learning representations via end-to-end structural understanding and fine-tuning on standard labeled corpora. In this paper, we introduce PromptNER, a new state-of-the-art algorithm for few-Shot and cross-domain NER. To adapt to any new NER task PromptNER requires a set of entity definitions in addition to the standard few-shot examples. Given a sentence, PromptNER prompts an LLM to produce a list of potential entities along with corresponding explanations justifying their compatibility with the provided entity type definitions. Remarkably, PromptNER achieves state-of-the-art performance on few-shot NER, achieving an 11% (absolute) improvement in F1 score on the ConLL dataset, and a 10% (absolute) improvement on the FewNERD dataset. PromptNER also moves the state of the art on Cross Domain NER, outperforming all prior methods (including those not limited to the few-shot setting), setting a new mark on all 5 CrossNER target domains, with an average F1 gain of 9%, despite using less than 2% of the available data.
NLP-80-标题: Language Model Tokenizers Introduce Unfairness Between Languages
作者: Aleksandar Petrov, Emanuele La Malfa, Philip H.S. Torr, Adel Bibi
备注: Project webpage: this https URL, Code: this https URL
Abstract: Recent language models have shown impressive multilingual performance, even when not explicitly trained for it. Despite this, concerns have been raised about the quality of their outputs across different languages. In this paper, we show how disparity in the treatment of different languages arises at the tokenization stage, well before a model is even invoked. The same text translated into different languages can have drastically different tokenization lengths, with differences up to 15 times in some cases. These disparities persist across the 17 tokenizers we evaluate, even if they are intentionally trained for multilingual support. Character-level and byte-level models also exhibit over 4 times the difference in the encoding length for some language pairs. This induces unfair treatment for some language communities in regard to the cost of accessing commercial language services, the processing time and latency, as well as the amount of content that can be provided as context to the models. Therefore, we make the case that we should train future language models using multilingually fair tokenizers.
NLP-81-标题: ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition INTERSPEECH2023
作者: Yuanchao Li, Zeyu Zhao, Ondrej Klejch, Peter Bell, Catherine Lai
备注: Accepted to INTERSPEECH 2023
Abstract: In Speech Emotion Recognition (SER), textual data is often used alongside audio signals to address their inherent variability. However, the reliance on human annotated text in most research hinders the development of practical SER systems. To overcome this challenge, we investigate how Automatic Speech Recognition (ASR) performs on emotional speech by analyzing the ASR performance on emotion corpora and examining the distribution of word errors and confidence scores in ASR transcripts to gain insight into how emotion affects ASR. We utilize four ASR systems, namely Kaldi ASR, wav2vec, Conformer, and Whisper, and three corpora: IEMOCAP, MOSI, and MELD to ensure generalizability. Additionally, we conduct text-based SER on ASR transcripts with increasing word error rates to investigate how ASR affects SER. The objective of this study is to uncover the relationship and mutual impact of ASR and SER, in order to facilitate ASR adaptation to emotional speech and the use of SER in real world.
NLP-82-标题: Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration INTERSPEECH
作者: Rustem Yeshpanov, Saida Mussakhojayeva, Yerbolat Khassanov
备注: 5 pages, 1 figure, 3 tables, accepted to Interspeech
Abstract: This work aims to build a multilingual text-to-speech (TTS) synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek. We specifically target the zero-shot learning scenario, where a TTS model trained using the data of one language is applied to synthesise speech for other, unseen languages. An end-to-end TTS system based on the Tacotron 2 architecture was trained using only the available data of the Kazakh language. To generate speech for the other Turkic languages, we first mapped the letters of the Turkic alphabets onto the symbols of the International Phonetic Alphabet (IPA), which were then converted to the Kazakh alphabet letters. To demonstrate the feasibility of the proposed approach, we evaluated the multilingual Turkic TTS model subjectively and obtained promising results. To enable replication of the experiments, we make our code and dataset publicly available in our GitHub repository.
ML-0-标题: Parallel Sampling of Diffusion Models
作者: Andy Shih, Suneel Belkhale, Stefano Ermon, Dorsa Sadigh, Nima Anari
Abstract: Diffusion models are powerful generative models but suffer from slow sampling, often taking 1000 sequential denoising steps for one sample. As a result, considerable efforts have been directed toward reducing the number of denoising steps, but these methods hurt sample quality. Instead of reducing the number of denoising steps (trading quality for speed), in this paper we explore an orthogonal approach: can we run the denoising steps in parallel (trading compute for speed)? In spite of the sequential nature of the denoising steps, we show that surprisingly it is possible to parallelize sampling via Picard iterations, by guessing the solution of future denoising steps and iteratively refining until convergence. With this insight, we present ParaDiGMS, a novel method to accelerate the sampling of pretrained diffusion models by denoising multiple steps in parallel. ParaDiGMS is the first diffusion sampling method that enables trading compute for speed and is even compatible with existing fast sampling techniques such as DDIM and DPMSolver. Using ParaDiGMS, we improve sampling speed by 2-4x across a range of robotics and image generation models, giving state-of-the-art sampling speeds of 0.2s on 100-step DiffusionPolicy and 16s on 1000-step StableDiffusion-v2 with no measurable degradation of task reward, FID score, or CLIP score.
ML-1-标题: Rectifying Group Irregularities in Explanations for Distribution Shift
作者: Adam Stein, Yinjun Wu, Eric Wong, Mayur Naik
备注: 19 pages, 5 figures
Abstract: It is well-known that real-world changes constituting distribution shift adversely affect model performance. How to characterize those changes in an interpretable manner is poorly understood. Existing techniques to address this problem take the form of shift explanations that elucidate how to map samples from the original distribution toward the shifted one by reducing the disparity between these two distributions. However, these methods can introduce group irregularities, leading to explanations that are less feasible and robust. To address these issues, we propose Group-aware Shift Explanations (GSE), a method that produces interpretable explanations by leveraging worst-group optimization to rectify group irregularities. We demonstrate how GSE not only maintains group structures, such as demographic and hierarchical subpopulations, but also enhances feasibility and robustness in the resulting explanations in a wide range of tabular, language, and image settings.
ML-2-标题: Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?
作者: Yutong He, Xinmeng Huang, Kun Yuan
Abstract: Communication compression is a common technique in distributed optimization that can alleviate communication overhead by transmitting compressed gradients and model parameters. However, compression can introduce information distortion, which slows down convergence and incurs more communication rounds to achieve desired solutions. Given the trade-off between lower per-round communication costs and additional rounds of communication, it is unclear whether communication compression reduces the total communication cost. This paper explores the conditions under which unbiased compression, a widely used form of compression, can reduce the total communication cost, as well as the extent to which it can do so. To this end, we present the first theoretical formulation for characterizing the total communication cost in distributed optimization with communication compression. We demonstrate that unbiased compression alone does not necessarily save the total communication cost, but this outcome can be achieved if the compressors used by all workers are further assumed independent. We establish lower bounds on the communication rounds required by algorithms using independent unbiased compressors to minimize smooth convex functions, and show that these lower bounds are tight by refining the analysis for ADIANA. Our results reveal that using independent unbiased compression can reduce the total communication cost by a factor of up to \Theta(\sqrt\min\n, \kappa) , where n is the number of workers and \kappa is the condition number of the functions being minimized. These theoretical findings are supported by experimental results.
ML-3-标题: A Guide Through the Zoo of Biased SGD
作者: Yury Demidovich, Grigory Malinovsky, Igor Sokolov, Peter Richtárik
备注: 55 pages, 2 figures, 10 tables
Abstract: Stochastic Gradient Descent (SGD) is arguably the most important single algorithm in modern machine learning. Although SGD with unbiased gradient estimators has been studied extensively over at least half a century, SGD variants relying on biased estimators are rare. Nevertheless, there has been an increased interest in this topic in recent years. However, existing literature on SGD with biased estimators (BiasedSGD) lacks coherence since each new paper relies on a different set of assumptions, without any clear understanding of how they are connected, which may lead to confusion. We address this gap by establishing connections among the existing assumptions, and presenting a comprehensive map of the underlying relationships. Additionally, we introduce a new set of assumptions that is provably weaker than all previous assumptions, and use it to present a thorough analysis of BiasedSGD in both convex and non-convex settings, offering advantages over previous results. We also provide examples where biased estimators outperform their unbiased counterparts or where unbiased versions are simply not available. Finally, we demonstrate the effectiveness of our framework through experimental results that validate our theoretical findings.
ML-4-标题: Sharpness-Aware Minimization Leads to Low-Rank Features
作者: Maksym Andriushchenko, Dara Bahri, Hossein Mobahi, Nicolas Flammarion
Abstract: Sharpness-aware minimization (SAM) is a recently proposed method that minimizes the sharpness of the training loss of a neural network. While its generalization improvement is well-known and is the primary motivation, we uncover an additional intriguing effect of SAM: reduction of the feature rank which happens at different layers of a neural network. We show that this low-rank effect occurs very broadly: for different architectures such as fully-connected networks, convolutional networks, vision transformers and for different objectives such as regression, classification, language-image contrastive training. To better understand this phenomenon, we provide a mechanistic understanding of how low-rank features arise in a simple two-layer network. We observe that a significant number of activations gets entirely pruned by SAM which directly contributes to the rank reduction. We confirm this effect theoretically and check that it can also occur in deep networks, although the overall rank reduction mechanism can be more complex, especially for deep networks with pre-activation skip connections and self-attention layers. We make our code available at this https URL.
ML-5-标题: Voyager: An Open-Ended Embodied Agent with Large Language Models
作者: Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar
备注: Project website and open-source codebase: this https URL
Abstract: We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by Voyager are temporally extended, interpretable, and compositional, which compounds the agent’s abilities rapidly and alleviates catastrophic forgetting. Empirically, Voyager shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing Minecraft. It obtains 3.3x more unique items, travels 2.3x longer distances, and unlocks key tech tree milestones up to 15.3x faster than prior SOTA. Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize. We open-source our full codebase and prompts at this https URL.
ML-6-标题: DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
作者: Ahmed Khaled, Konstantin Mishchenko, Chi Jin
备注: 23 pages, 1 table, 4 figures
Abstract: This paper proposes a new easy-to-implement parameter-free gradient-based optimizer: DoWG (Distance over Weighted Gradients). We prove that DoWG is efficient – matching the convergence rate of optimally tuned gradient descent in convex optimization up to a logarithmic factor without tuning any parameters, and universal – automatically adapting to both smooth and nonsmooth problems. While popular algorithms such as AdaGrad, Adam, or DoG compute a running average of the squared gradients, DoWG maintains a new distance-based weighted version of the running average, which is crucial to achieve the desired properties. To our best knowledge, DoWG is the first parameter-free, efficient, and universal algorithm that does not require backtracking search procedures. It is also the first parameter-free AdaGrad style algorithm that adapts to smooth optimization. To complement our theory, we also show empirically that DoWG trains at the edge of stability, and validate its effectiveness on practical machine learning tasks. This paper further uncovers the underlying principle behind the success of the AdaGrad family of algorithms by presenting a novel analysis of Normalized Gradient Descent (NGD), that shows NGD adapts to smoothness when it exists, with no change to the stepsize. This establishes the universality of NGD and partially explains the empirical observation that it trains at the edge of stability in a much more general setup compared to standard gradient descent. The latter might be of independent interest to the community.
ML-7-标题: Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
作者: Florian E. Dorner, Nikola Konstantinov, Georgi Pashaliev, Martin Vechev
备注: 37 pages, 5 figures
Abstract: Collaborative learning techniques have the potential to enable training machine learning models that are superior to models trained on a single entity’s data. However, in many cases, potential participants in such collaborative schemes are competitors on a downstream task, such as firms that each aim to attract customers by providing the best recommendations. This can incentivize dishonest updates that damage other participants’ models, potentially undermining the benefits of collaboration. In this work, we formulate a game that models such interactions and study two learning tasks within this framework: single-round mean estimation and multi-round SGD on strongly-convex objectives. For a natural class of player actions, we show that rational clients are incentivized to strongly manipulate their updates, preventing learning. We then propose mechanisms that incentivize honest communication and ensure learning quality comparable to full cooperation. Lastly, we empirically demonstrate the effectiveness of our incentive scheme on a standard non-convex federated learning benchmark. Our work shows that explicitly modeling the incentives and actions of dishonest clients, rather than assuming them malicious, can enable strong robustness guarantees for collaborative learning.
ML-8-标题: Fast Online Node Labeling for Very Large Graphs ICML2023
作者: Baojian Zhou, Yifan Sun, Reza Babanezhad
备注: 40 pages,17 figures, ICML 2023
Abstract: This paper studies the online node classification problem under a transductive learning setting. Current methods either invert a graph kernel matrix with \mathcalO(n^3) runtime and \mathcalO(n^2) space complexity or sample a large volume of random spanning trees, thus are difficult to scale to large graphs. In this work, we propose an improvement based on the \textitonline relaxation technique introduced by a series of works (Rakhlin et al.,2012; Rakhlin and Sridharan, 2015; 2017). We first prove an effective regret \mathcalO(\sqrtn^1+\gamma) when suitable parameterized graph kernels are chosen, then propose an approximate algorithm FastONL enjoying \mathcalO(k\sqrtn^1+\gamma) regret based on this relaxation. The key of FastONL is a \textitgeneralized local push method that effectively approximates inverse matrix columns and applies to a series of popular kernels. Furthermore, the per-prediction cost is \mathcalO(\textvol(\mathcalS)\log 1/\epsilon) locally dependent on the graph with linear memory cost. Experiments show that our scalable method enjoys a better tradeoff between local and global consistency.
ML-9-标题: Distributed TD(0) with Almost No Communication
作者: Rui Liu, Alex Olshevsky
备注: This is a shortened version of arXiv:2104.07855
Abstract: We provide a new non-asymptotic analysis of distributed temporal difference learning with linear function approximation. Our approach relies on ``one-shot averaging,‘’ where N agents run identical local copies of the TD(0) method and average the outcomes only once at the very end. We demonstrate a version of the linear time speedup phenomenon, where the convergence time of the distributed process is a factor of N faster than the convergence time of TD(0). This is the first result proving benefits from parallelism for temporal difference methods.
ML-10-标题: Persistent Laplacian-enhanced Algorithm for Scarcely Labeled Data Classification
作者: Gokul Bhusal, Ekaterina Merkurjev, Guo-Wei Wei
Abstract: The success of many machine learning (ML) methods depends crucially on having large amounts of labeled data. However, obtaining enough labeled data can be expensive, time-consuming, and subject to ethical constraints for many applications. One approach that has shown tremendous value in addressing this challenge is semi-supervised learning (SSL); this technique utilizes both labeled and unlabeled data during training, often with much less labeled data than unlabeled data, which is often relatively easy and inexpensive to obtain. In fact, SSL methods are particularly useful in applications where the cost of labeling data is especially expensive, such as medical analysis, natural language processing (NLP), or speech recognition. A subset of SSL methods that have achieved great success in various domains involves algorithms that integrate graph-based techniques. These procedures are popular due to the vast amount of information provided by the graphical framework and the versatility of their applications. In this work, we propose an algebraic topology-based semi-supervised method called persistent Laplacian-enhanced graph MBO (PL-MBO) by integrating persistent spectral graph theory with the classical Merriman-Bence- Osher (MBO) scheme. Specifically, we use a filtration procedure to generate a sequence of chain complexes and associated families of simplicial complexes, from which we construct a family of persistent Laplacians. Overall, it is a very efficient procedure that requires much less labeled data to perform well compared to many ML techniques, and it can be adapted for both small and large datasets. We evaluate the performance of the proposed method on data classification, and the results indicate that the proposed technique outperforms other existing semi-supervised algorithms.
ML-11-标题: Gaussian Processes with State-Dependent Noise for Stochastic Control
作者: Marcel Menner, Karl Berntorp
Abstract: This paper considers a stochastic control framework, in which the residual model uncertainty of the dynamical system is learned using a Gaussian Process (GP). In the proposed formulation, the residual model uncertainty consists of a nonlinear function and state-dependent noise. The proposed formulation uses a posterior-GP to approximate the residual model uncertainty and a prior-GP to account for state-dependent noise. The two GPs are interdependent and are thus learned jointly using an iterative algorithm. Theoretical properties of the iterative algorithm are established. Advantages of the proposed state-dependent formulation include (i) faster convergence of the GP estimate to the unknown function as the GP learns which data samples are more trustworthy and (ii) an accurate estimate of state-dependent noise, which can, e.g., be useful for a controller or decision-maker to determine the uncertainty of an action. Simulation studies highlight these two advantages.
ML-12-标题: Beyond Reward: Offline Preference-guided Policy Optimization
作者: Yachen Kang, Diyuan Shi, Jinxin Liu, Li He, Donglin Wang
Abstract: This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online interaction or specification of reward functions. Instead, the agent is provided with pre-existing offline trajectories and human preferences between pairs of trajectories to extract the dynamics and task information, respectively. Since the dynamics and task information are orthogonal, a naive approach would involve using preference-based reward learning followed by an off-the-shelf offline RL algorithm. However, this requires the separate learning of a scalar reward function, which is assumed to be an information bottleneck. To address this issue, we propose the offline preference-guided policy optimization (OPPO) paradigm, which models offline trajectories and preferences in a one-step process, eliminating the need for separately learning a reward function. OPPO achieves this by introducing an offline hindsight information matching objective for optimizing a contextual policy and a preference modeling objective for finding the optimal context. OPPO further integrates a well-performing decision policy by optimizing the two objectives iteratively. Our empirical results demonstrate that OPPO effectively models offline preferences and outperforms prior competing baselines, including offline RL algorithms performed over either true or pseudo reward function specifications. Our code is available at this https URL .
ML-13-标题: Koopman Kernel Regression
作者: Petar Bevanda, Max Beier, Armin Lederer, Stefan Sosnowski, Eyke Hüllermeier, Sandra Hirche
Abstract: Many machine learning approaches for decision making, such as reinforcement learning, rely on simulators or predictive models to forecast the time-evolution of quantities of interest, e.g., the state of an agent or the reward of a policy. Forecasts of such complex phenomena are commonly described by highly nonlinear dynamical systems, making their use in optimization-based decision-making challenging. Koopman operator theory offers a beneficial paradigm for addressing this problem by characterizing forecasts via linear dynamical systems. This makes system analysis and long-term predictions simple – involving only matrix multiplications. However, the transformation to a linear system is generally non-trivial and unknown, requiring learning-based approaches. While there exists a variety of approaches, they usually lack crucial learning-theoretic guarantees, such that the behavior of the obtained models with increasing data and dimensionality is often unclear. We address the aforementioned by deriving a novel reproducing kernel Hilbert space (RKHS) that solely spans transformations into linear dynamical systems. The resulting Koopman Kernel Regression (KKR) framework enables the use of statistical learning tools from function approximation for novel convergence results and generalization risk bounds under weaker assumptions than existing work. Our numerical experiments indicate advantages over state-of-the-art statistical learning approaches for Koopman-based predictors.
ML-14-标题: C-MCTS: Safe Planning with Monte Carlo Tree Search
作者: Dinesh Parthasarathy, Georgios Kontes, Axel Plinge, Christopher Mutschler
备注: 13 pages
Abstract: Many real-world decision-making tasks, such as safety-critical scenarios, cannot be fully described in a single-objective setting using the Markov Decision Process (MDP) framework, as they include hard constraints. These can instead be modeled with additional cost functions within the Constrained Markov Decision Process (CMDP) framework. Even though CMDPs have been extensively studied in the Reinforcement Learning literature, little attention has been given to sampling-based planning algorithms such as MCTS for solving them. Previous approaches use Monte Carlo cost estimates to avoid constraint violations. However, these suffer from high variance which results in conservative performance with respect to costs. We propose Constrained MCTS (C-MCTS), an algorithm that estimates cost using a safety critic. The safety critic training is based on Temporal Difference learning in an offline phase prior to agent deployment. This critic limits the exploration of the search tree and removes unsafe trajectories within MCTS during deployment. C-MCTS satisfies cost constraints but operates closer to the constraint boundary, achieving higher rewards compared to previous work. As a nice byproduct, the planner is more efficient requiring fewer planning steps. Most importantly, we show that under model mismatch between the planner and the real world, our approach is less susceptible to cost violations than previous work.
ML-15-标题: DP-SGD Without Clipping: The Lipschitz Neural Network Way
作者: Louis Bethune, Thomas Massena, Thibaut Boissin, Yannick Prudent, Corentin Friedrich, Franck Mamalet, Aurelien Bellet, Mathieu Serrurier, David Vigouroux
备注: 39 pages, preprint
Abstract: State-of-the-art approaches for training Differentially Private (DP) Deep Neural Networks (DNN) faces difficulties to estimate tight bounds on the sensitivity of the network’s layers, and instead rely on a process of per-sample gradient clipping. This clipping process not only biases the direction of gradients but also proves costly both in memory consumption and in computation. To provide sensitivity bounds and bypass the drawbacks of the clipping process, our theoretical analysis of Lipschitz constrained networks reveals an unexplored link between the Lipschitz constant with respect to their input and the one with respect to their parameters. By bounding the Lipschitz constant of each layer with respect to its parameters we guarantee DP training of these networks. This analysis not only allows the computation of the aforementioned sensitivities at scale but also provides leads on to how maximize the gradient-to-noise ratio for fixed privacy guarantees. To facilitate the application of Lipschitz networks and foster robust and certifiable learning under privacy guarantees, we provide a Python package that implements building blocks allowing the construction and private training of such networks.
ML-16-标题: Optimization and Interpretability of Graph Attention Networks for Small Sparse Graph Structures in Automotive Applications
作者: Marion Neumeier, Andreas Tollkühn, Sebastian Dorn, Michael Botsch, Wolfgang Utschick
备注: Accepted as a conference paper in IEEE IV 2023, Anchorage, Alaska, USA
Abstract: For automotive applications, the Graph Attention Network (GAT) is a prominently used architecture to include relational information of a traffic scenario during feature embedding. As shown in this work, however, one of the most popular GAT realizations, namely GATv2, has potential pitfalls that hinder an optimal parameter learning. Especially for small and sparse graph structures a proper optimization is problematic. To surpass limitations, this work proposes architectural modifications of GATv2. In controlled experiments, it is shown that the proposed model adaptions improve prediction performance in a node-level regression task and make it more robust to parameter initialization. This work aims for a better understanding of the attention mechanism and analyzes its interpretability of identifying causal importance.
ML-17-标题: Explainability Techniques for Chemical Language Models
作者: Stefan Hödl, William Robinson, Yoram Bachrach, Wilhelm Huck, Tal Kachman
Abstract: Explainability techniques are crucial in gaining insights into the reasons behind the predictions of deep learning models, which have not yet been applied to chemical language models. We propose an explainable AI technique that attributes the importance of individual atoms towards the predictions made by these models. Our method backpropagates the relevance information towards the chemical input string and visualizes the importance of individual atoms. We focus on self-attention Transformers operating on molecular string representations and leverage a pretrained encoder for finetuning. We showcase the method by predicting and visualizing solubility in water and organic solvents. We achieve competitive model performance while obtaining interpretable predictions, which we use to inspect the pretrained model.
ML-18-标题: Martian time-series unraveled: A multi-scale nested approach with factorial variational autoencoders
作者: Ali Siahkoohi, Rudy Morel, Randall Balestriero, Erwan Allys, Grégory Sainton, Taichi Kawamura, Maarten V. de Hoop
Abstract: Unsupervised source separation involves unraveling an unknown set of source signals recorded through a mixing operator, with limited prior knowledge about the sources, and only access to a dataset of signal mixtures. This problem is inherently ill-posed and is further challenged by the variety of time-scales exhibited by sources in time series data. Existing methods typically rely on a preselected window size that limits their capacity to handle multi-scale sources. To address this issue, instead of operating in the time domain, we propose an unsupervised multi-scale clustering and source separation framework by leveraging wavelet scattering covariances that provide a low-dimensional representation of stochastic processes, capable of distinguishing between different non-Gaussian stochastic processes. Nested within this representation space, we develop a factorial Gaussian-mixture variational autoencoder that is trained to (1) probabilistically cluster sources at different time-scales and (2) independently sample scattering covariance representations associated with each cluster. Using samples from each cluster as prior information, we formulate source separation as an optimization problem in the wavelet scattering covariance representation space, resulting in separated sources in the time domain. When applied to seismic data recorded during the NASA InSight mission on Mars, our multi-scale nested approach proves to be a powerful tool for discriminating between sources varying greatly in time-scale, e.g., minute-long transient one-sided pulses (known as ``glitches’') and structured ambient noises resulting from atmospheric activities that typically last for tens of minutes. These results provide an opportunity to conduct further investigations into the isolated sources related to atmospheric-surface interactions, thermal relaxations, and other complex phenomena.
ML-19-标题: Dropout Drops Double Descent
作者: Tian-Le Yang, Joe Suzuki
Abstract: In this paper, we find and analyze that we can easily drop the double descent by only adding one dropout layer before the fully-connected linear layer. The surprising double-descent phenomenon has drawn public attention in recent years, making the prediction error rise and drop as we increase either sample or model size. The current paper shows that it is possible to alleviate these phenomena by using optimal dropout in the linear regression model and the nonlinear random feature regression, both theoretically and empirically. % y=X\beta^0+\epsilon with X\in\mathbbR^n\times p . We obtain the optimal dropout hyperparameter by estimating the ground truth \beta^0 with generalized ridge typed estimator \hat\beta=(X^TX+\alpha\cdot\mathrmdiag(X^TX))^-1X^Ty . Moreover, we empirically show that optimal dropout can achieve a monotonic test error curve in nonlinear neural networks using Fashion-MNIST and CIFAR-10. Our results suggest considering dropout for risk curve scaling when meeting the peak phenomenon. In addition, we figure out why previous deep learning models do not encounter double-descent scenarios – because we already apply a usual regularization approach like the dropout in our models. To our best knowledge, this paper is the first to analyze the relationship between dropout and double descent.
ML-20-标题: From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
作者: Claudio Battiloro, Indro Spinelli, Lev Telyatnikov, Michael Bronstein, Simone Scardapane, Paolo Di Lorenzo
备注: Under review. 17 pages, 5 figures
Abstract: Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networks (GNNs) on a given graph topology by dynamically learning it. However, most of LGI methods assume to have a (noisy, incomplete, improvable, …) input graph to rewire and can solely learn regular graph topologies. In the wake of the success of Topological Deep Learning (TDL), we study Latent Topology Inference (LTI) for learning higher-order cell complexes (with sparse and not regular topology) describing multi-way interactions between data points. To this aim, we introduce the Differentiable Cell Complex Module (DCM), a novel learnable function that computes cell probabilities in the complex to improve the downstream task. We show how to integrate DCM with cell complex message passing networks layers and train it in a end-to-end fashion, thanks to a two-step inference procedure that avoids an exhaustive search across all possible cells in the input, thus maintaining scalability. Our model is tested on several homophilic and heterophilic graph datasets and it is shown to outperform other state-of-the-art techniques, offering significant improvements especially in cases where an input graph is not provided.
ML-21-标题: Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration ICML2023
作者: Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen
备注: Accepted to ICML 2023
Abstract: Since the control of the Lipschitz constant has a great impact on the training stability, generalization, and robustness of neural networks, the estimation of this value is nowadays a real scientific challenge. In this paper we introduce a precise, fast, and differentiable upper bound for the spectral norm of convolutional layers using circulant matrix theory and a new alternative to the Power iteration. Called the Gram iteration, our approach exhibits a superlinear convergence. First, we show through a comprehensive set of experiments that our approach outperforms other state-of-the-art methods in terms of precision, computational cost, and scalability. Then, it proves highly effective for the Lipschitz regularization of convolutional neural networks, with competitive results against concurrent approaches.
ML-22-标题: A Conceptual Model for End-to-End Causal Discovery in Knowledge Tracing
作者: Nischal Ashok Kumar, Wanyong Feng, Jaewook Lee, Hunter McNichols, Aritra Ghosh, Andrew Lan
备注: 16th International Conference on Educational Data Mining (EDM 2023)
Abstract: In this paper, we take a preliminary step towards solving the problem of causal discovery in knowledge tracing, i.e., finding the underlying causal relationship among different skills from real-world student response data. This problem is important since it can potentially help us understand the causal relationship between different skills without extensive A/B testing, which can potentially help educators to design better curricula according to skill prerequisite information. Specifically, we propose a conceptual solution, a novel causal gated recurrent unit (GRU) module in a modified deep knowledge tracing model, which uses i) a learnable permutation matrix for causal ordering among skills and ii) an optionally learnable lower-triangular matrix for causal structure among skills. We also detail how to learn the model parameters in an end-to-end, differentiable way. Our solution placed among the top entries in Task 3 of the NeurIPS 2022 Challenge on Causal Insights for Learning Paths in Education. We detail preliminary experiments as evaluated on the challenge’s public leaderboard since the ground truth causal structure has not been publicly released, making detailed local evaluation impossible.
ML-23-标题: Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms GECCO2023
作者: Connor Mattson, Daniel S. Brown
备注: 13 pages, 10 figures, To be published in Proceedings Genetic and Evolutionary Computation Conference (GECCO 2023)
Abstract: Robot swarms often exhibit emergent behaviors that are fascinating to observe; however, it is often difficult to predict what swarm behaviors can emerge under a given set of agent capabilities. We seek to efficiently leverage human input to automatically discover a taxonomy of collective behaviors that can emerge from a particular multi-agent system, without requiring the human to know beforehand what behaviors are interesting or even possible. Our proposed approach adapts to user preferences by learning a similarity space over swarm collective behaviors using self-supervised learning and human-in-the-loop queries. We combine our learned similarity metric with novelty search and clustering to explore and categorize the space of possible swarm behaviors. We also propose several general-purpose heuristics that improve the efficiency of our novelty search by prioritizing robot controllers that are likely to lead to interesting emergent behaviors. We test our approach in simulation on two robot capability models and show that our methods consistently discover a richer set of emergent behaviors than prior work. Code, videos, and datasets are available at this https URL.
ML-24-标题: Learning Safety Constraints from Demonstrations with Unknown Rewards
作者: David Lindner, Xin Chen, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
Abstract: We propose Convex Constraint Learning for Reinforcement Learning (CoCoRL), a novel approach for inferring shared constraints in a Constrained Markov Decision Process (CMDP) from a set of safe demonstrations with possibly different reward functions. While previous work is limited to demonstrations with known rewards or fully known environment dynamics, CoCoRL can learn constraints from demonstrations with different unknown rewards without knowledge of the environment dynamics. CoCoRL constructs a convex safe set based on demonstrations, which provably guarantees safety even for potentially sub-optimal (but safe) demonstrations. For near-optimal demonstrations, CoCoRL converges to the true safe set with no policy regret. We evaluate CoCoRL in tabular environments and a continuous driving simulation with multiple constraints. CoCoRL learns constraints that lead to safe driving behavior and that can be transferred to different tasks and environments. In contrast, alternative methods based on Inverse Reinforcement Learning (IRL) often exhibit poor performance and learn unsafe policies.
ML-25-标题: SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control AAMAS2023
作者: Harsh Goel, Yifeng Zhang, Mehul Damani, Guillaume Sartoretti
备注: To appear in the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)
Abstract: Many recent works have turned to multi-agent reinforcement learning (MARL) for adaptive traffic signal control to optimize the travel time of vehicles over large urban networks. However, achieving effective and scalable cooperation among junctions (agents) remains an open challenge, as existing methods often rely on extensive, non-generalizable reward shaping or on non-scalable centralized learning. To address these problems, we propose a new MARL method for traffic signal control, SocialLight, which learns cooperative traffic control policies by distributedly estimating the individual marginal contribution of agents on their local neighborhood. SocialLight relies on the Asynchronous Actor Critic (A3C) framework, and makes learning scalable by learning a locally-centralized critic conditioned over the states and actions of neighboring agents, used by agents to estimate individual contributions by counterfactual reasoning. We further introduce important modifications to the advantage calculation that help stabilize policy updates. These modifications decouple the impact of the neighbors’ actions on the computed advantages, thereby reducing the variance in the gradient updates. We benchmark our trained network against state-of-the-art traffic signal control methods on standard benchmarks in two traffic simulators, SUMO and CityFlow. Our results show that SocialLight exhibits improved scalability to larger road networks and better performance across usual traffic metrics.
ML-26-标题: Condensed Prototype Replay for Class Incremental Learning
作者: Jiangtao Kong, Zhenyu Zong, Tianyi Zhou, Huajie Shao
Abstract: Incremental learning (IL) suffers from catastrophic forgetting of old tasks when learning new tasks. This can be addressed by replaying previous tasks’ data stored in a memory, which however is usually prone to size limits and privacy leakage. Recent studies store only class centroids as prototypes and augment them with Gaussian noises to create synthetic data for replay. However, they cannot effectively avoid class interference near their margins that leads to forgetting. Moreover, the injected noises distort the rich structure between real data and prototypes, hence even detrimental to IL. In this paper, we propose YONO that You Only Need to replay One condensed prototype per class, which for the first time can even outperform memory-costly exemplar-replay methods. To this end, we develop a novel prototype learning method that (1) searches for more representative prototypes in high-density regions by an attentional mean-shift algorithm and (2) moves samples in each class to their prototype to form a compact cluster distant from other classes. Thereby, the class margins are maximized, which effectively reduces interference causing future forgetting. In addition, we extend YONO to YONO+, which creates synthetic replay data by random sampling in the neighborhood of each prototype in the representation space. We show that the synthetic data can further improve YONO. Extensive experiments on IL benchmarks demonstrate the advantages of YONO/YONO+ over existing IL methods in terms of both accuracy and forgetting.
ML-27-标题: Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning ICML2023
作者: Hongzuo Xu, Yijie Wang, Juhui Wei, Songlei Jian, Yizhou Li, Ning Liu
备注: Accepted by ICML 2023
Abstract: Due to the unsupervised nature of anomaly detection, the key to fueling deep models is finding supervisory signals. Different from current reconstruction-guided generative models and transformation-based contrastive models, we devise novel data-driven supervision for tabular data by introducing a characteristic – scale – as data labels. By representing varied sub-vectors of data instances, we define scale as the relationship between the dimensionality of original sub-vectors and that of representations. Scales serve as labels attached to transformed representations, thus offering ample labeled data for neural network training. This paper further proposes a scale learning-based anomaly detection method. Supervised by the learning objective of scale distribution alignment, our approach learns the ranking of representations converted from varied subspaces of each data instance. Through this proxy task, our approach models inherent regularities and patterns within data, which well describes data “normality”. Abnormal degrees of testing instances are obtained by measuring whether they fit these learned patterns. Extensive experiments show that our approach leads to significant improvement over state-of-the-art generative/contrastive anomaly detection methods.
ML-28-标题: Demystifying Oversmoothing in Attention-Based Graph Neural Networks
作者: Xinyi Wu, Amir Ajorlou, Zihui Wu, Ali Jadbabaie
Abstract: Oversmoothing in Graph Neural Networks (GNNs) refers to the phenomenon where increasing network depth leads to homogeneous node representations. While previous work has established that Graph Convolutional Networks (GCNs) exponentially lose expressive power, it remains controversial whether the graph attention mechanism can mitigate oversmoothing. In this work, we provide a definitive answer to this question through a rigorous mathematical analysis, by viewing attention-based GNNs as nonlinear time-varying dynamical systems and incorporating tools and techniques from the theory of products of inhomogeneous matrices and the joint spectral radius. We establish that, contrary to popular belief, the graph attention mechanism cannot prevent oversmoothing and loses expressive power exponentially. The proposed framework extends the existing results on oversmoothing for symmetric GCNs to a significantly broader class of GNN models. In particular, our analysis accounts for asymmetric, state-dependent and time-varying aggregation operators and a wide range of common nonlinear activation functions, such as ReLU, LeakyReLU, GELU and SiLU.
ML-29-标题: FAVAS: Federated AVeraging with ASynchronous clients
作者: Louis Leconte, Van Minh Nguyen, Eric Moulines
Abstract: In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVAS, for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity,
classical'' federated learning faces the increasingly difficult task of scaling synchronous communication over large wireless networks. Moreover, clients typically have different computing resources and therefore computing speed, which can lead to a significant bias (in favor of fast’’ clients) when the updates are asynchronous. Therefore, practical deployment of FL requires to handle users with strongly varying computing speed in communication/resource constrained setting. We provide convergence guarantees for FAVAS in a smooth, non-convex environment and carefully compare the obtained convergence guarantees with existing bounds, when they are available. Experimental results show that the FAVAS algorithm outperforms current methods on standard benchmarks.
ML-30-标题: On Influence Functions Classification Influence Relative Influence Memorization and Generalization
作者: Michael Kounavis, Ousmane Dia, Ilqar Ramazanli
Abstract: Machine learning systems such as large scale recommendation systems or natural language processing systems are usually trained on billions of training points and are associated with hundreds of billions or trillions of parameters. Improving the learning process in such a way that both the training load is reduced and the model accuracy improved is highly desired. In this paper we take a first step toward solving this problem, studying influence functions from the perspective of simplifying the computations they involve. We discuss assumptions, under which influence computations can be performed on significantly fewer parameters. We also demonstrate that the sign of the influence value can indicate whether a training point is to memorize, as opposed to generalize upon. For this purpose we formally define what memorization means for a training point, as opposed to generalization. We conclude that influence functions can be made practical, even for large scale machine learning systems, and that influence values can be taken into account by algorithms that selectively remove training points, as part of the learning process.
ML-31-标题: Combinatorial Bandits for Maximum Value Reward Function under Max Value-Index Feedback
作者: Yiliu Wang, Wei Chen, Milan Vojnović
Abstract: We consider a combinatorial multi-armed bandit problem for maximum value reward function under maximum value and index feedback. This is a new feedback structure that lies in between commonly studied semi-bandit and full-bandit feedback structures. We propose an algorithm and provide a regret bound for problem instances with stochastic arm outcomes according to arbitrary distributions with finite supports. The regret analysis rests on considering an extended set of arms, associated with values and probabilities of arm outcomes, and applying a smoothness condition. Our algorithm achieves a O((k/\Delta)\log(T)) distribution-dependent and a \tildeO(\sqrtT) distribution-independent regret where k is the number of arms selected in each round, \Delta is a distribution-dependent reward gap and T is the horizon time. Perhaps surprisingly, the regret bound is comparable to previously-known bound under more informative semi-bandit feedback. We demonstrate the effectiveness of our algorithm through experimental results.
ML-32-标题: Markov Decision Process with an External Temporal Process
作者: Ranga Shaarad Ayyagari, Ambedkar Dukkipati
Abstract: Most reinforcement learning algorithms treat the context under which they operate as a stationary, isolated and undisturbed environment. However, in the real world, the environment is constantly changing due to a variety of external influences. To address this problem, we study Markov Decision Processes (MDP) under the influence of an external temporal process. We formalize this notion and discuss conditions under which the problem becomes tractable with suitable solutions. We propose a policy iteration algorithm to solve this problem and theoretically analyze its performance.
ML-33-标题: Strategic Data Sharing between Competitors
作者: Nikita Tsoy, Nikola Konstantinov
Abstract: Collaborative learning techniques have significantly advanced in recent years, enabling private model training across multiple organizations. Despite this opportunity, firms face a dilemma when considering data sharing with competitors – while collaboration can improve a company’s machine learning model, it may also benefit competitors and hence reduce profits. In this work, we introduce a general framework for analyzing this data-sharing trade-off. The framework consists of three components, representing the firms’ production decisions, the effect of additional data on model quality, and the data-sharing negotiation process, respectively. We then study an instantiation of the framework, based on a conventional market model from economic theory, to identify key factors that affect collaboration incentives. Our findings indicate a profound impact of market conditions on the data-sharing incentives. In particular, we find that reduced competition, in terms of the similarities between the firms’ products, and harder learning tasks foster collaboration.
ML-34-标题: Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks
作者: Gehua Ma, Rui Yan, Huajin Tang
Abstract: Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have emerged as pillar models in neuromorphic intelligence. Despite extensive research on spiking neural networks (SNNs), most are established on deterministic models. Integrating noise into SNNs leads to biophysically more realistic neural dynamics and may benefit model performance. This work presents the noisy spiking neural network (NSNN) and the noise-driven learning rule (NDL) by introducing a spiking neuron model incorporating noisy neuronal dynamics. Our approach shows how noise may act as a resource for computation and learning and theoretically provides a framework for general SNNs. Moreover, NDL provides an insightful rationale for surrogate gradients. By incorporating various SNN architectures and algorithms, we show that our approach exhibits competitive performance and improved robustness against challenging perturbations than deterministic SNNs. Additionally, we demonstrate the utility of the NSNN model for neural coding studies. Overall, NSNN offers a powerful, flexible, and easy-to-use tool for machine learning practitioners and computational neuroscience researchers.
ML-35-标题: Ordered and Binary Speaker Embedding INTERSPEECH2023
作者: Jiaying Wang, Xianglong Wang, Namin Wang, Lantian Li, Dong Wang
备注: to be published in INTERSPEECH 2023
Abstract: Modern speaker recognition systems represent utterances by embedding vectors. Conventional embedding vectors are dense and non-structural. In this paper, we propose an ordered binary embedding approach that sorts the dimensions of the embedding vector via a nested dropout and converts the sorted vectors to binary codes via Bernoulli sampling. The resultant ordered binary codes offer some important merits such as hierarchical clustering, reduced memory usage, and fast retrieval. These merits were empirically verified by comprehensive experiments on a speaker identification task with the VoxCeleb and CN-Celeb datasets.
ML-36-标题: Implicit bias of SGD in L_2-regularized linear DNNs: One-way jumps from high to low rank
作者: Zihan Wang, Arthur Jacot
Abstract: The L_2 -regularized loss of Deep Linear Networks (DLNs) with more than one hidden layers has multiple local minima, corresponding to matrices with different ranks. In tasks such as matrix completion, the goal is to converge to the local minimum with the smallest rank that still fits the training data. While rank-underestimating minima can easily be avoided since they do not fit the data, gradient descent might get stuck at rank-overestimating minima. We show that with SGD, there is always a probability to jump from a higher rank minimum to a lower rank one, but the probability of jumping back is zero. More precisely, we define a sequence of sets B_1\subset B_2\subset\cdots\subset B_R so that B_r contains all minima of rank r or less (and not more) that are absorbing for small enough ridge parameters \lambda and learning rates \eta : SGD has prob. 0 of leaving B_r , and from any starting point there is a non-zero prob. for SGD to go in B_r .
ML-37-标题: Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score ICML2023
作者: Shuhai Zhang, Feng Liu, Jiahao Yang, Yifan Yang, Changsheng Li, Bo Han, Mingkui Tan
备注: Accepted at ICML 2023
Abstract: Adversarial detection aims to determine whether a given sample is an adversarial one based on the discrepancy between natural and adversarial distributions. Unfortunately, estimating or comparing two data distributions is extremely difficult, especially in high-dimension spaces. Recently, the gradient of log probability density (a.k.a., score) w.r.t. the sample is used as an alternative statistic to compute. However, we find that the score is sensitive in identifying adversarial samples due to insufficient information with one sample only. In this paper, we propose a new statistic called expected perturbation score (EPS), which is essentially the expected score of a sample after various perturbations. Specifically, to obtain adequate information regarding one sample, we perturb it by adding various noises to capture its multi-view observations. We theoretically prove that EPS is a proper statistic to compute the discrepancy between two samples under mild conditions. In practice, we can use a pre-trained diffusion model to estimate EPS for each sample. Last, we propose an EPS-based adversarial detection (EPS-AD) method, in which we develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples. We also prove that the EPS-based MMD between natural and adversarial samples is larger than that among natural samples. Extensive experiments show the superior adversarial detection performance of our EPS-AD.
ML-38-标题: Online and Streaming Algorithms for Constrained k-Submodular Maximization
作者: Fabian Spaeh, Alina Ene, Huy L. Nguyen
Abstract: Constrained k -submodular maximization is a general framework that captures many discrete optimization problems such as ad allocation, influence maximization, personalized recommendation, and many others. In many of these applications, datasets are large or decisions need to be made in an online manner, which motivates the development of efficient streaming and online algorithms. In this work, we develop single-pass streaming and online algorithms for constrained k -submodular maximization with both monotone and general (possibly non-monotone) objectives subject to cardinality and knapsack constraints. Our algorithms achieve provable constant-factor approximation guarantees which improve upon the state of the art in almost all settings. Moreover, they are combinatorial and very efficient, and have optimal space and running time. We experimentally evaluate our algorithms on instances for ad allocation and other applications, where we observe that our algorithms are efficient and scalable, and construct solutions that are comparable in value to offline greedy algorithms.
ML-39-标题: SING: A Plug-and-Play DNN Learning Technique
作者: Adrien Courtois, Damien Scieur, Jean-Michel Morel, Pablo Arias, Thomas Eboli
Abstract: We propose SING (StabIlized and Normalized Gradient), a plug-and-play technique that improves the stability and generalization of the Adam(W) optimizer. SING is straightforward to implement and has minimal computational overhead, requiring only a layer-wise standardization of the gradients fed to Adam(W) without introducing additional hyper-parameters. We support the effectiveness and practicality of the proposed approach by showing improved results on a wide range of architectures, problems (such as image classification, depth estimation, and natural language processing), and in combination with other optimizers. We provide a theoretical analysis of the convergence of the method, and we show that by virtue of the standardization, SING can escape local minima narrower than a threshold that is inversely proportional to the network’s depth.
ML-40-标题: A graphon-signal analysis of graph neural networks
作者: Ron Levie
Abstract: We present an approach for analyzing message passing graph neural networks (MPNNs) based on an extension of graphon analysis to a so called graphon-signal analysis. A MPNN is a function that takes a graph and a signal on the graph (a graph-signal) and returns some value. Since the input space of MPNNs is non-Euclidean, i.e., graphs can be of any size and topology, properties such as generalization are less well understood for MPNNs than for Euclidean neural networks. We claim that one important missing ingredient in past work is a meaningful notion of graph-signal similarity measure, that endows the space of inputs to MPNNs with a regular structure. We present such a similarity measure, called the graphon-signal cut distance, which makes the space of all graph-signals a dense subset of a compact metric space – the graphon-signal space. Informally, two deterministic graph-signals are close in cut distance if they ``look like’’ they were sampled from the same random graph-signal model. Hence, our cut distance is a natural notion of graph-signal similarity, which allows comparing any pair of graph-signals of any size and topology. We prove that MPNNs are Lipschitz continuous functions over the graphon-signal metric space. We then give two applications of this result: 1) a generalization bound for MPNNs, and, 2) the stability of MPNNs to subsampling of graph-signals. Our results apply to any regular enough MPNN on any distribution of graph-signals, making the analysis rather universal.
ML-41-标题: Dynamic Inter-treatment Information Sharing for Heterogeneous Treatment Effects Estimation
作者: Vinod Kumar Chauhan, Jiandong Zhou, Soheila Molaei, Ghadeer Ghosheh, David A. Clifton
备注: (under review)
Abstract: Existing heterogeneous treatment effects learners, also known as conditional average treatment effects (CATE) learners, lack a general mechanism for end-to-end inter-treatment information sharing, and data have to be split among potential outcome functions to train CATE learners which can lead to biased estimates with limited observational datasets. To address this issue, we propose a novel deep learning-based framework to train CATE learners that facilitates dynamic end-to-end information sharing among treatment groups. The framework is based on \textitsoft weight sharing of \textithypernetworks, which offers advantages such as parameter efficiency, faster training, and improved results. The proposed framework complements existing CATE learners and introduces a new class of uncertainty-aware CATE learners that we refer to as \textitHyperCATE. We develop HyperCATE versions of commonly used CATE learners and evaluate them on IHDP, ACIC-2016, and Twins benchmarks. Our experimental results show that the proposed framework improves the CATE estimation error via counterfactual inference, with increasing effectiveness for smaller datasets.
ML-42-标题: Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies
作者: Jonas Teufel, Luca Torresi, Pascal Friederich
备注: 22 pages, accepted at xAI conference 2023 Portugal
Abstract: Despite the increasing relevance of explainable AI, assessing the quality of explanations remains a challenging issue. Due to the high costs associated with human-subject experiments, various proxy metrics are often used to approximately quantify explanation quality. Generally, one possible interpretation of the quality of an explanation is its inherent value for teaching a related concept to a student. In this work, we extend artificial simulatability studies to the domain of graph neural networks. Instead of costly human trials, we use explanation-supervisable graph neural networks to perform simulatability studies to quantify the inherent usefulness of attributional graph explanations. We perform an extensive ablation study to investigate the conditions under which the proposed analyses are most meaningful. We additionally validate our methods applicability on real-world graph classification and regression datasets. We find that relevant explanations can significantly boost the sample efficiency of graph neural networks and analyze the robustness towards noise and bias in the explanations. We believe that the notion of usefulness obtained from our proposed simulatability analysis provides a dimension of explanation quality that is largely orthogonal to the common practice of faithfulness and has great potential to expand the toolbox of explanation quality assessments, specifically for graph explanations.
ML-43-标题: Online learning of long range dependencies
作者: Nicolas Zucchet, Robert Meier, Simon Schug, Asier Mujika, João Sacramento
Abstract: Online learning holds the promise of enabling efficient long-term credit assignment in recurrent neural networks. However, current algorithms fall short of offline backpropagation by either not being scalable or failing to learn long-range dependencies. Here we present a high-performance online learning algorithm that merely doubles the memory and computational requirements of a single inference pass. We achieve this by leveraging independent recurrent modules in multi-layer networks, an architectural motif that has recently been shown to be particularly powerful. Experiments on synthetic memory problems and on the challenging long-range arena benchmark suite reveal that our algorithm performs competitively, establishing a new standard for what can be achieved through online learning. This ability to learn long-range dependencies offers a new perspective on learning in the brain and opens a promising avenue in neuromorphic computing.
ML-44-标题: How to Turn Your Knowledge Graph Embeddings into Generative Models via Probabilistic Circuits
作者: Lorenzo Loconte, Nicola Di Mauro, Robert Peharz, Antonio Vergari
Abstract: Some of the most successful knowledge graph embedding (KGE) models for link prediction – CP, RESCAL, TuckER, ComplEx – can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical constraints. This work re-interprets the score functions of these KGEs as circuits – constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs. Our interpretation comes with little or no loss of performance for link prediction, while the circuits framework unlocks exact learning by MLE, efficient sampling of new triples, and guarantee that logical constraints are satisfied by design. Furthermore, our models scale more gracefully than the original KGEs on graphs with millions of entities.
ML-45-标题: Learning DAGs from Data with Few Root Causes
作者: Panagiotis Misiakos, Chris Wendler, Markus Püschel
Abstract: We present a novel perspective and algorithm for learning directed acyclic graphs (DAGs) from data generated by a linear structural equation model (SEM). First, we show that a linear SEM can be viewed as a linear transform that, in prior work, computes the data from a dense input vector of random valued root causes (as we will call them) associated with the nodes. Instead, we consider the case of (approximately) few root causes and also introduce noise in the measurement of the data. Intuitively, this means that the DAG data is produced by few data-generating events whose effect percolates through the DAG. We prove identifiability in this new setting and show that the true DAG is the global minimizer of the L^0 -norm of the vector of root causes. For data with few root causes, with and without noise, we show superior performance compared to prior DAG learning methods.
ML-46-标题: End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
作者: Alexandre Maraval, Matthieu Zimmer, Antoine Grosnit, Haitham Bou Ammar
Abstract: Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function independently, joint training of both components remains an open challenge. This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data. Early on, we notice that training transformer-based neural processes from scratch with RL is challenging due to insufficient supervision, especially when rewards are sparse. We formalise this claim with a combinatorial analysis showing that the widely used notion of regret as a reward signal exhibits a logarithmic sparsity pattern in trajectory lengths. To tackle this problem, we augment the RL objective with an auxiliary task that guides part of the architecture to learn a valid probabilistic model as an inductive bias. We demonstrate that our method achieves state-of-the-art regret results against various baselines in experiments on standard hyperparameter optimisation tasks and also outperforms others in the real-world problems of mixed-integer programming tuning, antibody design, and logic synthesis for electronic design automation.
ML-47-标题: Learning Directed Graphical Models with Optimal Transport
作者: Vy Vo, Trung Le, Long-Tung Vuong, He Zhao, Edwin Bonilla, Dinh Phung
Abstract: Estimating the parameters of a probabilistic directed graphical model from incomplete data remains a long-standing challenge. This is because, in the presence of latent variables, both the likelihood function and posterior distribution are intractable without further assumptions about structural dependencies or model classes. While existing learning methods are fundamentally based on likelihood maximization, here we offer a new view of the parameter learning problem through the lens of optimal transport. This perspective licenses a framework that operates on many directed graphs without making unrealistic assumptions on the posterior over the latent variables or resorting to black-box variational approximations. We develop a theoretical framework and support it with extensive empirical evidence demonstrating the flexibility and versatility of our approach. Across experiments, we show that not only can our method recover the ground-truth parameters but it also performs competitively on downstream applications, notably the non-trivial task of discrete representation learning.
ML-48-标题: Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation ICML2023
作者: Ilan Naiman, Nimrod Berman, Omri Azencot
备注: Accepted to ICML 2023; The first two authors contributed equally
Abstract: Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, where data is time-dependent. However, the latter methods employ modality-based data augmentations and random sampling or solve auxiliary tasks. In this work, we propose to avoid that by generating, sampling, and comparing empirical distributions from the underlying variational model. Unlike existing work, we introduce a self-supervised sequential disentanglement framework based on contrastive estimation with no external signals, while using common batch sizes and samples from the latent space itself. In practice, we propose a unified, efficient, and easy-to-code sampling strategy for semantically similar and dissimilar views of the data. We evaluate our approach on video, audio, and time series benchmarks. Our method presents state-of-the-art results in comparison to existing techniques. The code is available at this https URL.
ML-49-标题: Neural Characteristic Activation Value Analysis for Improved ReLU Network Feature Learning
作者: Wenlin Chen, Hong Ge
备注: 16 pages, 4 figures, 3 tables. Preprint, under review
Abstract: We examine the characteristic activation values of individual ReLU units in neural networks. We refer to the corresponding set for such characteristic activation values in the input space as the characteristic activation set of a ReLU unit. We draw an explicit connection between the characteristic activation set and learned features in ReLU networks. This connection leads to new insights into why various neural network normalization techniques used in modern deep learning architectures regularize and stabilize SGD optimization. Utilizing these insights, we propose a geometric approach to parameterize ReLU networks for improved feature learning. We empirically verify its usefulness with less carefully chosen initialization schemes and larger learning rates. We report improved optimization stability, faster convergence speed, and better generalization performance.
ML-50-标题: Double Descent of Discrepancy: A Task- Data- and Model-Agnostic Phenomenon
作者: Yifan Luo, Bin Dong
Abstract: In this paper, we studied two identically-trained neural networks (i.e. networks with the same architecture, trained on the same dataset using the same algorithm, but with different initialization) and found that their outputs discrepancy on the training dataset exhibits a “double descent” phenomenon. We demonstrated through extensive experiments across various tasks, datasets, and network architectures that this phenomenon is prevalent. Leveraging this phenomenon, we proposed a new early stopping criterion and developed a new method for data quality assessment. Our results show that a phenomenon-driven approach can benefit deep learning research both in theoretical understanding and practical applications.
ML-51-标题: Empirical Optimal Transport between Conditional Distributions
作者: Piyushi Manupriya, Rachit Keerti Das, Sayantan Biswas, Shivam Chandhok, Saketha Nath Jagarlapudi
Abstract: Given samples from two joint distributions, we consider the problem of Optimal Transportation (OT) between the corresponding distributions conditioned on a common variable. The objective of this work is to estimate the associated transport cost (Wasserstein distance) as well as the transport plan between the conditionals as a function of the conditioned value. Since matching conditional distributions is at the core of supervised training of discriminative models and (implicit) conditional-generative models, OT between conditionals has the potential to be employed in diverse machine learning applications. However, since the conditionals involved in OT are implicitly specified via the joint samples, it is challenging to formulate this problem, especially when (i) the variable conditioned on is continuous and (ii) the marginal of this variable in the two distributions is different. We overcome these challenges by employing a specific kernel MMD (Maximum Mean Discrepancy) based regularizer that ensures the marginals of our conditional transport plan are close to the conditionals specified via the given joint samples. Under mild conditions, we prove that our estimator for this regularized transport cost is statistically consistent and derive finite-sample bounds on the estimation error. Application-specific details for parameterizing our conditional transport plan are also presented. Furthermore, we empirically evaluate our methodology on benchmark datasets in applications like classification, prompt learning for few-shot classification, and conditional-generation in the context of predicting cell responses to cancer treatment.
ML-52-标题: Quantitatively Measuring and Contrastive ly Exploring Heterogeneity for Domain Generalization KDD2023
作者: Yunze Tong, Junkun Yuan, Min Zhang, Didi Zhu, Keli Zhang, Fei Wu, Kun Kuang
备注: This paper has been accepted by KDD 2023
Abstract: Domain generalization (DG) is a prevalent problem in real-world applications, which aims to train well-generalized models for unseen target domains by utilizing several source domains. Since domain labels, i.e., which domain each data point is sampled from, naturally exist, most DG algorithms treat them as a kind of supervision information to improve the generalization performance. However, the original domain labels may not be the optimal supervision signal due to the lack of domain heterogeneity, i.e., the diversity among domains. For example, a sample in one domain may be closer to another domain, its original label thus can be the noise to disturb the generalization learning. Although some methods try to solve it by re-dividing domains and applying the newly generated dividing pattern, the pattern they choose may not be the most heterogeneous due to the lack of the metric for heterogeneity. In this paper, we point out that domain heterogeneity mainly lies in variant features under the invariant learning framework. With contrastive learning, we propose a learning potential-guided metric for domain heterogeneity by promoting learning variant features. Then we notice the differences between seeking variance-based heterogeneity and training invariance-based generalizable model. We thus propose a novel method called Heterogeneity-based Two-stage Contrastive Learning (HTCL) for the DG task. In the first stage, we generate the most heterogeneous dividing pattern with our contrastive metric. In the second stage, we employ an invariance-aimed contrastive learning by re-building pairs with the stable relation hinted by domains and classes, which better utilizes generated domain labels for generalization learning. Extensive experiments show HTCL better digs heterogeneity and yields great generalization performance.
ML-53-标题: Generative Adversarial Reduced Order Modelling
作者: Dario Coscia, Nicola Demo, Gianluigi Rozza
Abstract: In this work, we present GAROM, a new approach for reduced order modelling (ROM) based on generative adversarial networks (GANs). GANs have the potential to learn data distribution and generate more realistic data. While widely applied in many areas of deep learning, little research is done on their application for ROM, i.e. approximating a high-fidelity model with a simpler one. In this work, we combine the GAN and ROM framework, by introducing a data-driven generative adversarial model able to learn solutions to parametric differential equations. The latter is achieved by modelling the discriminator network as an autoencoder, extracting relevant features of the input, and applying a conditioning mechanism to the generator and discriminator networks specifying the differential equation parameters. We show how to apply our methodology for inference, provide experimental evidence of the model generalisation, and perform a convergence study of the method.
ML-54-标题: Exponential Smoothing for Off-Policy Learning ICML2023
作者: Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba
备注: ICML 2023 (Oral and Poster)
Abstract: Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we investigate a smooth regularization for IPS, for which we derive a two-sided PAC-Bayes generalization bound. The bound is tractable, scalable, interpretable and provides learning certificates. In particular, it is also valid for standard IPS without making the assumption that the importance weights are bounded. We demonstrate the relevance of our approach and its favorable performance through a set of learning tasks. Since our bound holds for standard IPS, we are able to provide insight into when regularizing IPS is useful. Namely, we identify cases where regularization might not be needed. This goes against the belief that, in practice, clipped IPS often enjoys favorable performance than standard IPS in OPL.
ML-55-标题: LLHR: Low Latency and High Reliability CNN Distributed Inference for Resource-Constrained UAV Swarms
作者: Marwan Dhuheir, Aiman Erbad, Sinan Sabeeh
备注: arXiv admin note: substantial text overlap with arXiv:2212.11201
Abstract: Recently, Unmanned Aerial Vehicles (UAVs) have shown impressive performance in many critical applications, such as surveillance, search and rescue operations, environmental monitoring, etc. In many of these applications, the UAVs capture images as well as other sensory data and then send the data processing requests to remote servers. Nevertheless, this approach is not always practical in real-time-based applications due to unstable connections, limited bandwidth, limited energy, and strict end-to-end latency. One promising solution is to divide the inference requests into subtasks that can be distributed among UAVs in a swarm based on the available resources. Moreover, these tasks create intermediate results that need to be transmitted reliably as the swarm moves to cover the area. Our system model deals with real-time requests, aiming to find the optimal transmission power that guarantees higher reliability and low latency. We formulate the Low Latency and High-Reliability (LLHR) distributed inference as an optimization problem, and due to the complexity of the problem, we divide it into three subproblems. In the first subproblem, we find the optimal transmit power of the connected UAVs with guaranteed transmission reliability. The second subproblem aims to find the optimal positions of the UAVs in the grid, while the last subproblem finds the optimal placement of the CNN layers in the available UAVs. We conduct extensive simulations and compare our work to two baseline models demonstrating that our model outperforms the competing models.
ML-56-标题: Stochastic Modified Equations and Dynamics of Dropout Algorithm
作者: Zhongwang Zhang, Yuqing Li, Tao Luo, Zhi-Qin John Xu
Abstract: Dropout is a widely utilized regularization technique in the training of neural networks, nevertheless, its underlying mechanism and its impact on achieving good generalization abilities remain poorly understood. In this work, we derive the stochastic modified equations for analyzing the dynamics of dropout, where its discrete iteration process is approximated by a class of stochastic differential equations. In order to investigate the underlying mechanism by which dropout facilitates the identification of flatter minima, we study the noise structure of the derived stochastic modified equation for dropout. By drawing upon the structural resemblance between the Hessian and covariance through several intuitive approximations, we empirically demonstrate the universal presence of the inverse variance-flatness relation and the Hessian-variance relation, throughout the training process of dropout. These theoretical and empirical findings make a substantial contribution to our understanding of the inherent tendency of dropout to locate flatter minima.
ML-57-标题: TabGSL: Graph Structure Learning for Tabular Data Prediction
作者: Jay Chiehen Liao, Cheng-Te Li
Abstract: This work presents a novel approach to tabular data prediction leveraging graph structure learning and graph neural networks. Despite the prevalence of tabular data in real-world applications, traditional deep learning methods often overlook the potentially valuable associations between data instances. Such associations can offer beneficial insights for classification tasks, as instances may exhibit similar patterns of correlations among features and target labels. This information can be exploited by graph neural networks, necessitating robust graph structures. However, existing studies primarily focus on improving graph structure from noisy data, largely neglecting the possibility of deriving graph structures from tabular data. We present a novel solution, Tabular Graph Structure Learning (TabGSL), to enhance tabular data prediction by simultaneously learning instance correlation and feature interaction within a unified framework. This is achieved through a proposed graph contrastive learning module, along with transformer-based feature extractor and graph neural network. Comprehensive experiments conducted on 30 benchmark tabular datasets demonstrate that TabGSL markedly outperforms both tree-based models and recent deep learning-based tabular models. Visualizations of the learned instance embeddings further substantiate the effectiveness of TabGSL.
ML-58-标题: PDE: Enhancing Generalization via PDE with Adaptive Distributional Diffusion
作者: Yige Yuan, Bingbing Xu, Bo Lin, Liang Hou, Fei Sun, Huawei Shen, Xueqi Cheng
Abstract: The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones. Current methods, mainly based on the data-driven paradigm such as data augmentation, adversarial training, and noise injection, may encounter limited generalization due to model non-smoothness. In this paper, we propose to investigate generalization from a Partial Differential Equation (PDE) perspective, aiming to enhance it directly through the underlying function of neural networks, rather than focusing on adjusting input data. Specifically, we first establish the connection between neural network generalization and the smoothness of the solution to a specific PDE, namely ``transport equation’'. Building upon this, we propose a general framework that introduces adaptive distributional diffusion into transport equation to enhance the smoothness of its solution, thereby improving generalization. In the context of neural networks, we put this theoretical framework into practice as PDE+ (\textbfPDE with \textbfAdaptive \textbfDistributional \textbfDiffusion) which diffuses each sample into a distribution covering semantically similar inputs. This enables better coverage of potentially unobserved distributions in training, thus improving generalization beyond merely data-driven methods. The effectiveness of PDE+ is validated in extensive settings, including clean samples and various corruptions, demonstrating its superior performance compared to SOTA methods.
ML-59-标题: Towards Label Position Bias in Graph Neural Networks
作者: Haoyu Han, Xiaorui Liu, Feng Shi, MohamadAli Torkamani, Charu C. Aggarwal, Jiliang Tang
Abstract: Graph Neural Networks (GNNs) have emerged as a powerful tool for semi-supervised node classification tasks. However, recent studies have revealed various biases in GNNs stemming from both node features and graph topology. In this work, we uncover a new bias - label position bias, which indicates that the node closer to the labeled nodes tends to perform better. We introduce a new metric, the Label Proximity Score, to quantify this bias, and find that it is closely related to performance disparities. To address the label position bias, we propose a novel optimization framework for learning a label position unbiased graph structure, which can be applied to existing GNNs. Extensive experiments demonstrate that our proposed method not only outperforms backbone methods but also significantly mitigates the issue of label position bias in GNNs.
ML-60-标题: Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term KDD’23
作者: Yun Yue, Jiadi Jiang, Zhiling Ye, Ning Gao, Yongchao Liu, Ke Zhang
备注: 10 pages. Accepted as a conference paper at KDD '23
Abstract: Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization. In this paper, we revisit the loss of SAM and propose a more general method, called WSAM, by incorporating sharpness as a regularization term. We prove its generalization bound through the combination of PAC and Bayes-PAC techniques, and evaluate its performance on various public datasets. The results demonstrate that WSAM achieves improved generalization, or is at least highly competitive, compared to the vanilla optimizer, SAM and its variants. The code is available at this https URL.
ML-61-标题: Unifying gradient regularization for Heterogeneous Graph Neural Networks
作者: Xiao Yang, Xuejiao Zhao, Zhiqi Shen
Abstract: Heterogeneous Graph Neural Networks (HGNNs) are a class of powerful deep learning methods widely used to learn representations of heterogeneous graphs. Despite the fast development of HGNNs, they still face some challenges such as over-smoothing, and non-robustness. Previous studies have shown that these problems can be reduced by using gradient regularization methods. However, the existing gradient regularization methods focus on either graph topology or node features. There is no universal approach to integrate these features, which severely affects the efficiency of regularization. In addition, the inclusion of gradient regularization into HGNNs sometimes leads to some problems, such as an unstable training process, increased complexity and insufficient coverage regularized information. Furthermore, there is still short of a complete theoretical analysis of the effects of gradient regularization on HGNNs. In this paper, we propose a novel gradient regularization method called Grug, which iteratively applies regularization to the gradients generated by both propagated messages and the node features during the message-passing process. Grug provides a unified framework integrating graph topology and node features, based on which we conduct a detailed theoretical analysis of their effectiveness. Specifically, the theoretical analyses elaborate the advantages of Grug: 1) Decreasing sample variance during the training process (Stability); 2) Enhancing the generalization of the model (Universality); 3) Reducing the complexity of the model (Simplicity); 4) Improving the integrity and diversity of graph information utilization (Diversity). As a result, Grug has the potential to surpass the theoretical upper bounds set by DropMessage (AAAI-23 Distinguished Papers). In addition, we evaluate Grug on five public real-world datasets with two downstream tasks.
ML-62-标题: Lucy-SKG: Learning to Play Rocket League Efficiently Using Deep Reinforcement Learning
作者: Vasileios Moschopoulos, Pantelis Kyriakidis, Aristotelis Lazaridis, Ioannis Vlahavas
备注: 24 pages, 11 figures
Abstract: A successful tactic that is followed by the scientific community for advancing AI is to treat games as problems, which has been proven to lead to various breakthroughs. We adapt this strategy in order to study Rocket League, a widely popular but rather under-explored 3D multiplayer video game with a distinct physics engine and complex dynamics that pose a significant challenge in developing efficient and high-performance game-playing agents. In this paper, we present Lucy-SKG, a Reinforcement Learning-based model that learned how to play Rocket League in a sample-efficient manner, outperforming by a notable margin the two highest-ranking bots in this game, namely Necto (2022 bot champion) and its successor Nexto, thus becoming a state-of-the-art agent. Our contributions include: a) the development of a reward analysis and visualization library, b) novel parameterizable reward shape functions that capture the utility of complex reward types via our proposed Kinesthetic Reward Combination (KRC) technique, and c) design of auxiliary neural architectures for training on reward prediction and state representation tasks in an on-policy fashion for enhanced efficiency in learning speed and performance. By performing thorough ablation studies for each component of Lucy-SKG, we showed their independent effectiveness in overall performance. In doing so, we demonstrate the prospects and challenges of using sample-efficient Reinforcement Learning techniques for controlling complex dynamical systems under competitive team-based multiplayer conditions.
ML-63-标题: On Architectural Compression of Text-to-Image Diffusion Models
作者: Bo-Kyeong Kim, Hyoung-Kyu Song, Thibault Castells, Shinkook Choi
备注: 10 figures, 5 tables
Abstract: Exceptional text-to-image (T2I) generation results of Stable Diffusion models (SDMs) come with substantial computational demands. To resolve this issue, recent research on efficient SDMs has prioritized reducing the number of sampling steps and utilizing network quantization. Orthogonal to these directions, this study highlights the power of classical architectural compression for general-purpose T2I synthesis by introducing block-removed knowledge-distilled SDMs (BK-SDMs). We eliminate several residual and attention blocks from the U-Net of SDMs, obtaining over a 30% reduction in the number of parameters, MACs per sampling step, and latency. We conduct distillation-based pretraining with only 0.22M LAION pairs (fewer than 0.1% of the full training pairs) on a single A100 GPU. Despite being trained with limited resources, our compact models can imitate the original SDM by benefiting from transferred knowledge and achieve competitive results against larger multi-billion parameter models on the zero-shot MS-COCO benchmark. Moreover, we demonstrate the applicability of our lightweight pretrained models in personalized generation with DreamBooth finetuning.
ML-64-标题: Feature space reduction method for ultrahigh-dimensional multiclass data: Random forest-based multiround screening (RFMS)
作者: Gergely Hanczár, Marcell Stippinger, Dávid Hanák, Marcell T. Kurbucz, Olivér M. Törteli, Ágnes Chripkó, Zoltán Somogyvári
备注: 9 pages, 2 figures, 2 tables
Abstract: In recent years, numerous screening methods have been published for ultrahigh-dimensional data that contain hundreds of thousands of features; however, most of these features cannot handle data with thousands of classes. Prediction models built to authenticate users based on multichannel biometric data result in this type of problem. In this study, we present a novel method known as random forest-based multiround screening (RFMS) that can be effectively applied under such circumstances. The proposed algorithm divides the feature space into small subsets and executes a series of partial model builds. These partial models are used to implement tournament-based sorting and the selection of features based on their importance. To benchmark RFMS, a synthetic biometric feature space generator known as BiometricBlender is employed. Based on the results, the RFMS is on par with industry-standard feature screening methods while simultaneously possessing many advantages over these methods.
ML-65-标题: IDEA: Invariant Causal Defense for Graph Adversarial Robustness
作者: Shuchang Tao, Qi Cao, Huawei Shen, Yunfan Wu, Bingbing Xu, Xueqi Cheng
Abstract: Graph neural networks (GNNs) have achieved remarkable success in various tasks, however, their vulnerability to adversarial attacks raises concerns for the real-world applications. Existing defense methods can resist some attacks, but suffer unbearable performance degradation under other unknown attacks. This is due to their reliance on either limited observed adversarial examples to optimize (adversarial training) or specific heuristics to alter graph or model structures (graph purification or robust aggregation). In this paper, we propose an Invariant causal DEfense method against adversarial Attacks (IDEA), providing a new perspective to address this issue. The method aims to learn causal features that possess strong predictability for labels and invariant predictability across attacks, to achieve graph adversarial robustness. Through modeling and analyzing the causal relationships in graph adversarial attacks, we design two invariance objectives to learn the causal features. Extensive experiments demonstrate that our IDEA significantly outperforms all the baselines under both poisoning and evasion attacks on five benchmark datasets, highlighting the strong and invariant predictability of IDEA. The implementation of IDEA is available at https://anonymous.4open.science/r/IDEA_repo-666B.
ML-66-标题: Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting ICML2023
作者: Hilaf Hasson, Danielle C. Maddix, Yuyang Wang, Gaurav Gupta, Youngsuk Park
备注: ICML 2023
Abstract: Ensembling is among the most popular tools in machine learning (ML) due to its effectiveness in minimizing variance and thus improving generalization. Most ensembling methods for black-box base learners fall under the umbrella of “stacked generalization,” namely training an ML algorithm that takes the inferences from the base learners as input. While stacking has been widely applied in practice, its theoretical properties are poorly understood. In this paper, we prove a novel result, showing that choosing the best stacked generalization from a (finite or finite-dimensional) family of stacked generalizations based on cross-validated performance does not perform “much worse” than the oracle best. Our result strengthens and significantly extends the results in Van der Laan et al. (2007). Inspired by the theoretical analysis, we further propose a particular family of stacked generalizations in the context of probabilistic forecasting, each one with a different sensitivity for how much the ensemble weights are allowed to vary across items, timestamps in the forecast horizon, and quantiles. Experimental results demonstrate the performance gain of the proposed method.
ML-67-标题: AUC Optimization from Multiple Unlabeled Dataset s
作者: Yu Liu, Zheng Xie, Ming Li
Abstract: Weakly supervised learning aims to empower machine learning when the perfect supervision is unavailable, which has drawn great attention from researchers. Among various types of weak supervision, one of the most challenging cases is to learn from multiple unlabeled (U) datasets with only a little knowledge of the class priors, or U ^m learning for short. In this paper, we study the problem of building an AUC (area under ROC curve) optimization model from multiple unlabeled datasets, which maximizes the pairwise ranking ability of the classifier. We propose U ^m -AUC, an AUC optimization approach that converts the U ^m data into a multi-label AUC optimization problem, and can be trained efficiently. We show that the proposed U ^m -AUC is effective theoretically and empirically.
ML-68-标题: TLNets: Transformation Learning Networks for long-range time-series prediction
作者: Wei Wang, Yang Liu, Hao Sun
备注: 25 pages
Abstract: Time series prediction is a prevalent issue across various disciplines, such as meteorology, traffic surveillance, investment, and energy production and consumption. Many statistical and machine-learning strategies have been developed to tackle this problem. However, these approaches either lack explainability or exhibit less satisfactory performance when the prediction horizon increases. To this end, we propose a novel plan for the designing of networks’ architecture based on transformations, possessing the potential to achieve an enhanced receptive field in learning which brings benefits to fuse features across scales. In this context, we introduce four different transformation mechanisms as bases to construct the learning model including Fourier Transform (FT), Singular Value Decomposition (SVD), matrix multiplication and Conv block. Hence, we develop four learning models based on the above building blocks, namely, FT-Matrix, FT-SVD, FT-Conv, and Conv-SVD. Note that the FT and SVD blocks are capable of learning global information, while the Conv blocks focus on learning local information. The matrix block is sparsely designed to learn both global and local information simultaneously. The above Transformation Learning Networks (TLNets) have been extensively tested and compared with multiple baseline models based on several real-world datasets and showed clear potential in long-range time-series forecasting.
ML-69-标题: Union Subgraph Neural Networks
作者: Jiaxing Xu, Aihu Zhang, Qingtian Bian, Vijay Prakash Dwivedi, Yiping Ke
Abstract: Graph Neural Networks (GNNs) are widely used for graph representation learning in many application domains. The expressiveness of vanilla GNNs is upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) test as they operate on rooted subtrees through iterative message passing. In this paper, we empower GNNs by injecting neighbor-connectivity information extracted from a new type of substructure. We first investigate different kinds of connectivities existing in a local neighborhood and identify a substructure called union subgraph, which is able to capture the complete picture of the 1-hop neighborhood of an edge. We then design a shortest-path-based substructure descriptor that possesses three nice properties and can effectively encode the high-order connectivities in union subgraphs. By infusing the encoded neighbor connectivities, we propose a novel model, namely Union Subgraph Neural Network (UnionSNN), which is proven to be strictly more powerful than 1-WL in distinguishing non-isomorphic graphs. Additionally, the local encoding from union subgraphs can also be injected into arbitrary message-passing neural networks (MPNNs) and Transformer-based models as a plugin. Extensive experiments on 17 benchmarks of both graph-level and node-level tasks demonstrate that UnionSNN outperforms state-of-the-art baseline models, with competitive computational efficiency. The injection of our local encoding to existing models is able to boost the performance by up to 11.09%.
ML-70-标题: Robust Ante-hoc Graph Explainer using Bilevel Optimization
作者: Mert Kosan, Arlei Silva, Ambuj Singh
Abstract: Explaining the decisions made by machine learning models for high-stakes applications is critical for increasing transparency and guiding improvements to these decisions. This is particularly true in the case of models for graphs, where decisions often depend on complex patterns combining rich structural and attribute data. While recent work has focused on designing so-called post-hoc explainers, the question of what constitutes a good explanation remains open. One intuitive property is that explanations should be sufficiently informative to enable humans to approximately reproduce the predictions given the data. However, we show that post-hoc explanations do not achieve this goal as their explanations are highly dependent on fixed model parameters (e.g., learned GNN weights). To address this challenge, this paper proposes RAGE (Robust Ante-hoc Graph Explainer), a novel and flexible ante-hoc explainer designed to discover explanations for a broad class of graph neural networks using bilevel optimization. RAGE is able to efficiently identify explanations that contain the full information needed for prediction while still enabling humans to rank these explanations based on their influence. Our experiments, based on graph classification and regression, show that RAGE explanations are more robust than existing post-hoc and ante-hoc approaches and often achieve similar or better accuracy than state-of-the-art models.
ML-71-标题: Learning across Data Owners with Joint Differential Privacy
作者: Yangsibo Huang, Haotian Jiang, Daogao Liu, Mohammad Mahdian, Jieming Mao, Vahab Mirrokni
Abstract: In this paper, we study the setting in which data owners train machine learning models collaboratively under a privacy notion called joint differential privacy [Kearns et al., 2018]. In this setting, the model trained for each data owner j uses j ‘s data without privacy consideration and other owners’ data with differential privacy guarantees. This setting was initiated in [Jain et al., 2021] with a focus on linear regressions. In this paper, we study this setting for stochastic convex optimization (SCO). We present an algorithm that is a variant of DP-SGD [Song et al., 2013; Abadi et al., 2016] and provides theoretical bounds on its population loss. We compare our algorithm to several baselines and discuss for what parameter setups our algorithm is more preferred. We also empirically study joint differential privacy in the multi-class classification problem over two public datasets. Our empirical findings are well-connected to the insights from our theoretical results.
ML-72-标题: Efficient Neural Music Generation
作者: Max W. Y. Lam, Qiao Tian, Tang Li, Zongyu Yin, Siyuan Feng, Ming Tu, Yuliang Ji, Rui Xia, Mingbo Ma, Xuchen Song, Jitong Chen, Yuping Wang, Yuxuan Wang
Abstract: Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge. In this paper, we present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality meanwhile reducing 95.7% or 99.6% forward passes in MusicLM, respectively, for sampling 10s or 30s music. MeLoDy inherits the highest-level LM from MusicLM for semantic modeling, and applies a novel dual-path diffusion (DPD) model and an audio VAE-GAN to efficiently decode the conditioning semantic tokens into waveform. DPD is proposed to simultaneously model the coarse and fine acoustics by incorporating the semantic information into segments of latents effectively via cross-attention at each denoising step. Our experimental results suggest the superiority of MeLoDy, not only in its practical advantages on sampling speed and infinitely continuable generation, but also in its state-of-the-art musicality, audio quality, and text correlation. Our samples are available at this https URL.
ML-73-标题: pFedSim: Similarity-Aware Model Aggregation Towards Personalized Federated Learning
作者: Jiahao Tan, Yipeng Zhou, Gang Liu, Jessie Hui Wang, Shui Yu
Abstract: The federated learning (FL) paradigm emerges to preserve data privacy during model training by only exposing clients’ model parameters rather than original data. One of the biggest challenges in FL lies in the non-IID (not identical and independently distributed) data (a.k.a., data heterogeneity) distributed on clients. To address this challenge, various personalized FL (pFL) methods are proposed such as similarity-based aggregation and model decoupling. The former one aggregates models from clients of a similar data distribution. The later one decouples a neural network (NN) model into a feature extractor and a classifier. Personalization is captured by classifiers which are obtained by local training. To advance pFL, we propose a novel pFedSim (pFL based on model similarity) algorithm in this work by combining these two kinds of methods. More specifically, we decouple a NN model into a personalized feature extractor, obtained by aggregating models from similar clients, and a classifier, which is obtained by local training and used to estimate client similarity. Compared with the state-of-the-art baselines, the advantages of pFedSim include: 1) significantly improved model accuracy; 2) low communication and computation overhead; 3) a low risk of privacy leakage; 4) no requirement for any external public information. To demonstrate the superiority of pFedSim, extensive experiments are conducted on real datasets. The results validate the superb performance of our algorithm which can significantly outperform baselines under various heterogeneous data settings.
ML-74-标题: The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning
作者: Kaiwen Wang, Kevin Zhou, Runzhe Wu, Nathan Kallus, Wen Sun
Abstract: While distributional reinforcement learning (RL) has demonstrated empirical success, the question of when and why it is beneficial has remained unanswered. In this work, we provide one explanation for the benefits of distributional RL through the lens of small-loss bounds, which scale with the instance-dependent optimal cost. If the optimal cost is small, our bounds are stronger than those from non-distributional approaches. As warmup, we show that learning the cost distribution leads to small-loss regret bounds in contextual bandits (CB), and we find that distributional CB empirically outperforms the state-of-the-art on three challenging tasks. For online RL, we propose a distributional version-space algorithm that constructs confidence sets using maximum likelihood estimation, and we prove that it achieves small-loss regret in the tabular MDPs and enjoys small-loss PAC bounds in latent variable models. Building on similar insights, we propose a distributional offline RL algorithm based on the pessimism principle and prove that it enjoys small-loss PAC bounds, which exhibit a novel robustness property. For both online and offline RL, our results provide the first theoretical benefits of learning distributions even when we only need the mean for making decisions.
ML-75-标题: Detecting Dataset Drift and Non-IID Sampling via k-Nearest Neighbors
作者: Jesse Cummings, Elías Snorrason, Jonas Mueller
Abstract: We present a straightforward statistical test to detect certain violations of the assumption that the data are Independent and Identically Distributed (IID). The specific form of violation considered is common across real-world applications: whether the examples are ordered in the dataset such that almost adjacent examples tend to have more similar feature values (e.g. due to distributional drift, or attractive interactions between datapoints). Based on a k-Nearest Neighbors estimate, our approach can be used to audit any multivariate numeric data as well as other data types (image, text, audio, etc.) that can be numerically represented, perhaps with model embeddings. Compared with existing methods to detect drift or auto-correlation, our approach is both applicable to more types of data and also able to detect a wider variety of IID violations in practice. Code: this https URL
ML-76-标题: PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning
作者: Jianxiong Li, Xiao Hu, Haoran Xu, Jingjing Liu, Xianyuan Zhan, Ya-Qin Zhang
Abstract: Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance. However, existing methods, effective as they are, suffer from suboptimal performance, limited adaptability, and unsatisfactory computational efficiency. We propose a novel framework, PROTO, which overcomes the aforementioned limitations by augmenting the standard RL objective with an iteratively evolving regularization term. Performing a trust-region-style update, PROTO yields stable initial finetuning and optimal final performance by gradually evolving the regularization term to relax the constraint strength. By adjusting only a few lines of code, PROTO can bridge any offline policy pretraining and standard off-policy RL finetuning to form a powerful offline-to-online RL pathway, birthing great adaptability to diverse methods. Simple yet elegant, PROTO imposes minimal additional computation and enables highly efficient online finetuning. Extensive experiments demonstrate that PROTO achieves superior performance over SOTA baselines, offering an adaptable and efficient offline-to-online RL framework.
ML-77-标题: How to escape sharp minima
作者: Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra
备注: 27 pages, 1 figure; Comments would be appreciated!
Abstract: Modern machine learning applications have seen a remarkable success of optimization algorithms that are designed to find flat minima. Motivated by this paradigm, this work formulates and studies the algorithmic question of how to find flat minima. As an initial effort, this work adopts the trace of hessian of the cost function as the measure of flatness, and formally defines the notion of approximate flat minima. Under this notion, we then design algorithms that find approximate flat minima efficiently. For general cost functions, we present a gradient-based algorithm that finds an approximate flat local minimum efficiently. The main component of the algorithm is to use gradients computed from randomly perturbed iterates to estimate a direction that leads to flatter minima. For the setting where the cost function is an empirical risk over training data, we present a faster algorithm that is inspired by a recently proposed practical algorithm called sharpness-aware minimization, supporting its success in practice.
ML-78-标题: Federated Composite Saddle Point Optimization
作者: Site Bai, Brian Bullins
Abstract: Federated learning (FL) approaches for saddle point problems (SPP) have recently gained in popularity due to the critical role they play in machine learning (ML). Existing works mostly target smooth unconstrained objectives in Euclidean space, whereas ML problems often involve constraints or non-smooth regularization, which results in a need for composite optimization. Addressing these issues, we propose Federated Dual Extrapolation (FeDualEx), an extra-step primal-dual algorithm, which is the first of its kind that encompasses both saddle point optimization and composite objectives under the FL paradigm. Both the convergence analysis and the empirical evaluation demonstrate the effectiveness of FeDualEx in these challenging settings. In addition, even for the sequential version of FeDualEx, we provide rates for the stochastic composite saddle point setting which, to our knowledge, are not found in prior literature.
ML-79-标题: A Robust Classifier Under Missing-Not-At-Random Sample Selection Bias
作者: Huy Mai, Wen Huang, Wei Du, Xintao Wu
备注: 12 pages
Abstract: The shift between the training and testing distributions is commonly due to sample selection bias, a type of bias caused by non-random sampling of examples to be included in the training set. Although there are many approaches proposed to learn a classifier under sample selection bias, few address the case where a subset of labels in the training set are missing-not-at-random (MNAR) as a result of the selection process. In statistics, Greene’s method formulates this type of sample selection with logistic regression as the prediction model. However, we find that simply integrating this method into a robust classification framework is not effective for this bias setting. In this paper, we propose BiasCorr, an algorithm that improves on Greene’s method by modifying the original training set in order for a classifier to learn under MNAR sample selection bias. We provide theoretical guarantee for the improvement of BiasCorr over Greene’s method by analyzing its bias. Experimental results on real-world datasets demonstrate that BiasCorr produces robust classifiers and can be extended to outperform state-of-the-art classifiers that have been proposed to train under sample selection bias.
ML-80-标题: Revisiting Generalized p-Laplacian Regularized Framelet GCNs: Convergence Energy Dynamic and Training with Non-Linear Diffusion
作者: Dai Shi, Zhiqi Shao, Yi Guo, Qibin Zhao, Junbin Gao
Abstract: This work presents a comprehensive theoretical analysis of graph p-Laplacian based framelet network (pL-UFG) to establish a solid understanding of its properties. We begin by conducting a convergence analysis of the p-Laplacian based implicit layer integrated after the framelet convolution, providing insights into the asymptotic behavior of pL-UFG. By exploring the generalized Dirichlet energy of pL-UFG, we demonstrate that the Dirichlet energy remains non-zero, ensuring the avoidance of over-smoothing issues in pL-UFG as it approaches convergence. Furthermore, we elucidate the dynamic energy perspective through which the implicit layer in pL-UFG synergizes with graph framelets, enhancing the model’s adaptability to both homophilic and heterophilic data. Remarkably, we establish that the implicit layer can be interpreted as a generalized non-linear diffusion process, enabling training using diverse schemes. These multifaceted analyses lead to unified conclusions that provide novel insights for understanding and implementing pL-UFG, contributing to advancements in the field of graph-based deep learning.
ML-81-标题: Patient Outcome Predictions Improve Operations at a Large Hospital Network
作者: Liangyuan Na, Kimberly Villalobos Carballo, Jean Pauphilet, Ali Haddad-Sisakht, Daniel Kombert, Melissa Boisjoli-Langlois, Andrew Castiglione, Maram Khalifa, Pooja Hebbal, Barry Stein, Dimitris Bertsimas
备注: 41 pages, 13 figures
Abstract: Problem definition: Access to accurate predictions of patients’ outcomes can enhance medical staff’s decision-making, which ultimately benefits all stakeholders in the hospitals. A large hospital network in the US has been collaborating with academics and consultants to predict short-term and long-term outcomes for all inpatients across their seven hospitals. Methodology/results: We develop machine learning models that predict the probabilities of next 24-hr/48-hr discharge and intensive care unit transfers, end-of-stay mortality and discharge dispositions. All models achieve high out-of-sample AUC (75.7%-92.5%) and are well calibrated. In addition, combining 48-hr discharge predictions with doctors’ predictions simultaneously enables more patient discharges (10%-28.7%) and fewer 7-day/30-day readmissions ( p -value <0.001 ). We implement an automated pipeline that extracts data and updates predictions every morning, as well as user-friendly software and a color-coded alert system to communicate these patient-level predictions (alongside explanations) to clinical teams. Managerial implications: Since we have been gradually deploying the tool, and training medical staff, over 200 doctors, nurses, and case managers across seven hospitals use it in their daily patient review process. We observe a significant reduction in the average length of stay (0.67 days per patient) following its adoption and anticipate substantial financial benefits (between \ 55 and \ 72 million annually) for the healthcare system.
ML-82-标题: GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint
作者: Paiheng Xu, Yuhang Zhou, Bang An, Wei Ai, Furong Huang
Abstract: Given the growing concerns about fairness in machine learning and the impressive performance of Graph Neural Networks (GNNs) on graph data learning, algorithmic fairness in GNNs has attracted significant attention. While many existing studies improve fairness at the group level, only a few works promote individual fairness, which renders similar outcomes for similar individuals. A desirable framework that promotes individual fairness should (1) balance between fairness and performance, (2) accommodate two commonly-used individual similarity measures (externally annotated and computed from input features), (3) generalize across various GNN models, and (4) be computationally efficient. Unfortunately, none of the prior work achieves all the desirables. In this work, we propose a novel method, GFairHint, which promotes individual fairness in GNNs and achieves all aforementioned desirables. GFairHint learns fairness representations through an auxiliary link prediction task, and then concatenates the representations with the learned node embeddings in original GNNs as a “fairness hint”. Through extensive experimental investigations on five real-world graph datasets under three prevalent GNN models covering both individual similarity measures above, GFairHint achieves the best fairness results in almost all combinations of datasets with various backbone models, while generating comparable utility results, with much less computational cost compared to the previous state-of-the-art (SoTA) method.
ML-83-标题: Matrix Estimation for Offline Reinforcement Learning with Low-Rank Structure
作者: Xumei Xi, Christina Lee Yu, Yudong Chen
Abstract: We consider offline Reinforcement Learning (RL), where the agent does not interact with the environment and must rely on offline data collected using a behavior policy. Previous works provide policy evaluation guarantees when the target policy to be evaluated is covered by the behavior policy, that is, state-action pairs visited by the target policy must also be visited by the behavior policy. We show that when the MDP has a latent low-rank structure, this coverage condition can be relaxed. Building on the connection to weighted matrix completion with non-uniform observations, we propose an offline policy evaluation algorithm that leverages the low-rank structure to estimate the values of uncovered state-action pairs. Our algorithm does not require a known feature representation, and our finite-sample error bound involves a novel discrepancy measure quantifying the discrepancy between the behavior and target policies in the spectral space. We provide concrete examples where our algorithm achieves accurate estimation while existing coverage conditions are not satisfied. Building on the above evaluation algorithm, we further design an offline policy optimization algorithm and provide non-asymptotic performance guarantees.
ML-84-标题: Debias Coarsely Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models
作者: Zhong Yi Wan, Ricardo Baptista, Yi-fan Chen, John Anderson, Anudhyan Boral, Fei Sha, Leonardo Zepeda-Núñez
备注: 32 pages
Abstract: We introduce a two-stage probabilistic framework for statistical downscaling between unpaired data. Statistical downscaling seeks a probabilistic map to transform low-resolution data from a (possibly biased) coarse-grained numerical scheme to high-resolution data that is consistent with a high-fidelity scheme. Our framework tackles the problem by tandeming two transformations: a debiasing step that is performed by an optimal transport map, and an upsampling step that is achieved by a probabilistic diffusion model with \textita posteriori conditional sampling. This approach characterizes a conditional distribution without the need for paired data, and faithfully recovers relevant physical statistics from biased samples. We demonstrate the utility of the proposed approach on one- and two-dimensional fluid flow problems, which are representative of the core difficulties present in numerical simulations of weather and climate. Our method produces realistic high-resolution outputs from low-resolution inputs, by upsampling resolutions of 8\times and 16\times . Moreover, our procedure correctly matches the statistics of physical quantities, even when the low-frequency content of the inputs and outputs do not match, a crucial but difficult-to-satisfy assumption needed by current state-of-the-art alternatives.
ML-85-标题: Reversible and irreversible bracket-based dynamics for deep graph neural networks
作者: Anthony Gruber, Kookjin Lee, Nathaniel Trask
Abstract: Recent works have shown that physics-inspired architectures allow the training of deep graph neural networks (GNNs) without oversmoothing. The role of these physics is unclear, however, with successful examples of both reversible (e.g., Hamiltonian) and irreversible (e.g., diffusion) phenomena producing comparable results despite diametrically opposed mechanisms, and further complications arising due to empirical departures from mathematical theory. This work presents a series of novel GNN architectures based upon structure-preserving bracket-based dynamical systems, which are provably guaranteed to either conserve energy or generate positive dissipation with increasing depth. It is shown that the theoretically principled framework employed here allows for inherently explainable constructions, which contextualize departures from theory in current architectures and better elucidate the roles of reversibility and irreversibility in network performance.
ML-86-标题: Reverse Engineering Self-Supervised Learning
作者: Ido Ben-Shaul, Ravid Shwartz-Ziv, Tomer Galanti, Shai Dekel, Yann LeCun
Abstract: Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge. This paper presents an in-depth empirical analysis of SSL-trained representations, encompassing diverse models, architectures, and hyperparameters. Our study reveals an intriguing aspect of the SSL training process: it inherently facilitates the clustering of samples with respect to semantic labels, which is surprisingly driven by the SSL objective’s regularization term. This clustering process not only enhances downstream classification but also compresses the data information. Furthermore, we establish that SSL-trained representations align more closely with semantic classes rather than random classes. Remarkably, we show that learned representations align with semantic classes across various hierarchical levels, and this alignment increases during training and when moving deeper into the network. Our findings provide valuable insights into SSL’s representation learning mechanisms and their impact on performance across different sets of classes.
ML-87-标题: Deep Equivariant Hyperspheres
作者: Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck, Andreas Robinson, Cuong Le
Abstract: This paper presents an approach to learning nD features equivariant under orthogonal transformations for point cloud analysis, utilizing hyperspheres and regular n-simplexes. Our main contributions are theoretical and tackle major issues in geometric deep learning such as equivariance and invariance under geometric transformations. Namely, we enrich the recently developed theory of steerable 3D spherical neurons – SO(3)-equivariant filter banks based on neurons with spherical decision surfaces – by extending said neurons to nD, which we call deep equivariant hyperspheres, and enabling their stacking in multiple layers. Using the ModelNet40 benchmark, we experimentally verify our theoretical contributions and show a potential practical configuration of the proposed equivariant hyperspheres.
ML-88-标题: Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning
作者: Jungtaek Kim
备注: 18 pages, 13 figures, 2 tables
Abstract: Bayesian optimization has attracted huge attention from diverse research areas in science and engineering, since it is capable of finding a global optimum of an expensive-to-evaluate black-box function efficiently. In general, a probabilistic regression model, e.g., Gaussian processes, random forests, and Bayesian neural networks, is widely used as a surrogate function to model an explicit distribution over function evaluations given an input to estimate and a training dataset. Beyond the probabilistic regression-based Bayesian optimization, density ratio estimation-based Bayesian optimization has been suggested in order to estimate a density ratio of the groups relatively close and relatively far to a global optimum. Developing this line of research further, a supervised classifier can be employed to estimate a class probability for the two groups instead of a density ratio. However, the supervised classifiers used in this strategy tend to be overconfident for a global solution candidate. To solve this overconfidence problem, we propose density ratio estimation-based Bayesian optimization with semi-supervised learning. Finally, we demonstrate the experimental results of our methods and several baseline methods in two distinct scenarios with unlabeled point sampling and a fixed-size pool.
ML-89-标题: Size Generalizability of Graph Neural Networks on Biological Data: Insights and Practices from the Spectral Perspective
作者: Yujun Yan, Gaotang Li, Danai koutra
备注: 17 pages, including appendix
Abstract: We investigate the question of whether the knowledge learned by graph neural networks (GNNs) from small graphs is generalizable to large graphs in the same domain. Prior works suggest that the distribution shift, particularly in the degree distribution, between graphs of different sizes can lead to performance degradation in the graph classification task. However, this may not be the case for biological datasets where the degrees are bounded and the distribution shift of degrees is small. Even with little degree distribution shift, our observations show that GNNs’ performance on larger graphs from the same datasets still degrades, suggesting other causes. In fact, there has been a lack of exploration in real datasets to understand the types and properties of distribution shifts caused by various graph sizes. Furthermore, previous analyses of size generalizability mostly focus on the spatial domain. To fill these gaps, we take the spectral perspective and study the size generalizability of GNNs on biological data. We identify a distribution shift between small and large graphs in the eigenvalues of the normalized Laplacian/adjacency matrix, indicating a difference in the global node connectivity, which is found to be correlated with the node closeness centrality. We further find that despite of the variations in global connectivity, graphs of different sizes share similar local connectivity, which can be utilized to improve the size generalizability of GNNs. Based on our spectral insights and empirical observations, we propose a model-agnostic strategy, SIA, which uses size-irrelevant local structural features, i.e., the local closeness centrality of a node, to guide the learning process. Our empirical results demonstrate that our strategy improves the graph classification performance of various GNNs on small and large graphs when training with only small graphs.
ML-90-标题: Learning Lagrangian Fluid Mechanics with E(3)-Equivariant Graph Neural Networks
作者: Artur P. Toshev, Gianluca Galletti, Johannes Brandstetter, Stefan Adami, Nikolaus A. Adams
备注: GSI’23 6th International Conference on Geometric Science of Information; 10 pages; oral. arXiv admin note: substantial text overlap with arXiv:2304.00150
Abstract: We contribute to the vastly growing field of machine learning for engineering systems by demonstrating that equivariant graph neural networks have the potential to learn more accurate dynamic-interaction models than their non-equivariant counterparts. We benchmark two well-studied fluid-flow systems, namely 3D decaying Taylor-Green vortex and 3D reverse Poiseuille flow, and evaluate the models based on different performance measures, such as kinetic energy or Sinkhorn distance. In addition, we investigate different embedding methods of physical-information histories for equivariant models. We find that while currently being rather slow to train and evaluate, equivariant models with our proposed history embeddings learn more accurate physical interactions.
ML-91-标题: Control invariant set enhanced safe reinforcement learning: improved sampling efficiency guaranteed stability and robustness
作者: Song Bo, Bernard T. Agyeman, Xunyuan Yin, Jinfeng Liu (University of Alberta)
备注: arXiv admin note: substantial text overlap with arXiv:2304.05509
Abstract: Reinforcement learning (RL) is an area of significant research interest, and safe RL in particular is attracting attention due to its ability to handle safety-driven constraints that are crucial for real-world applications. This work proposes a novel approach to RL training, called control invariant set (CIS) enhanced RL, which leverages the advantages of utilizing the explicit form of CIS to improve stability guarantees and sampling efficiency. Furthermore, the robustness of the proposed approach is investigated in the presence of uncertainty. The approach consists of two learning stages: offline and online. In the offline stage, CIS is incorporated into the reward design, initial state sampling, and state reset procedures. This incorporation of CIS facilitates improved sampling efficiency during the offline training process. In the online stage, RL is retrained whenever the predicted next step state is outside of the CIS, which serves as a stability criterion, by introducing a Safety Supervisor to examine the safety of the action and make necessary corrections. The stability analysis is conducted for both cases, with and without uncertainty. To evaluate the proposed approach, we apply it to a simulated chemical reactor. The results show a significant improvement in sampling efficiency during offline training and closed-loop stability guarantee in the online implementation, with and without uncertainty.
ML-92-标题: Linear Neural Network Layers Promote Learning Single- and Multiple-Index Models
作者: Suzanna Parkinson, Greg Ongie, Rebecca Willett
Abstract: This paper explores the implicit bias of overparameterized neural networks of depth greater than two layers. Our framework considers a family of networks of varying depths that all have the same capacity but different implicitly defined representation costs. The representation cost of a function induced by a neural network architecture is the minimum sum of squared weights needed for the network to represent the function; it reflects the function space bias associated with the architecture. Our results show that adding linear layers to a ReLU network yields a representation cost that favors functions that can be approximated by a low-rank linear operator composed with a function with low representation cost using a two-layer network. Specifically, using a neural network to fit training data with minimum representation cost yields an interpolating function that is nearly constant in directions orthogonal to a low-dimensional subspace. This means that the learned network will approximately be a single- or multiple-index model. Our experiments show that when this active subspace structure exists in the data, adding linear layers can improve generalization and result in a network that is well-aligned with the true active subspace.
ML-93-标题: Lightweight Learner for Shared Knowledge Lifelong Learning
作者: Yunhao Ge, Yuecheng Li, Di Wu, Ao Xu, Adam M. Jones, Amanda Sofie Rios, Iordanis Fostiropoulos, Shixian Wen, Po-Hsuan Huang, Zachary William Murdock, Gozde Sahin, Shuo Ni, Kiran Lekkala, Sumedh Anand Sontakke, Laurent Itti
备注: Transactions on Machine Learning Research (TMLR) paper
Abstract: In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicated LL machinery is then deployed to mitigate the forgetting of old tasks as new tasks are learned. This is inherently slow. We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel. After learning their respective tasks, agents share and consolidate their knowledge over a decentralized communication network, so that, in the end, all agents can master all tasks. We present one solution to SKILL which uses Lightweight Lifelong Learning (LLL) agents, where the goal is to facilitate efficient sharing by minimizing the fraction of the agent that is specialized for any given task. Each LLL agent thus consists of a common task-agnostic immutable part, where most parameters are, and individual task-specific modules that contain fewer parameters but are adapted to each task. Agents share their task-specific modules, plus summary information (“task anchors”) representing their tasks in the common task-agnostic latent space of all agents. Receiving agents register each received task-specific module using the corresponding anchor. Thus, every agent improves its ability to solve new tasks each time new task-specific modules and anchors are received. On a new, very challenging SKILL-102 dataset with 102 image classification tasks (5,033 classes in total, 2,041,225 training, 243,464 validation, and 243,464 test images), we achieve much higher (and SOTA) accuracy over 8 LL baselines, while also achieving near perfect parallelization. Code and data can be found at this https URL
ML-94-标题: Manifold Diffusion Fields
作者: Ahmed A. Elhag, Joshua M. Susskind, Miguel Angel Bautista
Abstract: We present Manifold Diffusion Fields (MDF), an approach to learn generative models of continuous functions defined over Riemannian manifolds. Leveraging insights from spectral geometry analysis, we define an intrinsic coordinate system on the manifold via the eigen-functions of the Laplace-Beltrami Operator. MDF represents functions using an explicit parametrization formed by a set of multiple input-output pairs. Our approach allows to sample continuous functions on manifolds and is invariant with respect to rigid and isometric transformations of the manifold. Empirical results on several datasets and manifolds show that MDF can capture distributions of such functions with better diversity and fidelity than previous approaches.
ML-95-标题: The Behavior and Convergence of Local Bayesian Optimization
作者: Kaiwen Wu, Kyurae Kim, Roman Garnett, Jacob R. Gardner
备注: 24 pages
Abstract: A recent development in Bayesian optimization is the use of local optimization strategies, which can deliver strong empirical performance on high-dimensional problems compared to traditional global strategies. The “folk wisdom” in the literature is that the focus on local optimization sidesteps the curse of dimensionality; however, little is known concretely about the expected behavior or convergence of Bayesian local optimization routines. We first study the behavior of the local approach, and find that the statistics of individual local solutions of Gaussian process sample paths are surprisingly good compared to what we would expect to recover from global methods. We then present the first rigorous analysis of such a Bayesian local optimization algorithm recently proposed by Müller et al. (2021), and derive convergence rates in both the noisy and noiseless settings.
ML-96-标题: Sound Design Strategies for Latent Audio Space Explorations Using Deep Learning Architectures
作者: Kıvanç Tatar, Kelsey Cotton, Daniel Bisig
备注: In Proceedings of Sound and Music Computing 2023
Abstract: The research in Deep Learning applications in sound and music computing have gathered an interest in the recent years; however, there is still a missing link between these new technologies and on how they can be incorporated into real-world artistic practices. In this work, we explore a well-known Deep Learning architecture called Variational Autoencoders (VAEs). These architectures have been used in many areas for generating latent spaces where data points are organized so that similar data points locate closer to each other. Previously, VAEs have been used for generating latent timbre spaces or latent spaces of symbolic music excepts. Applying VAE to audio features of timbre requires a vocoder to transform the timbre generated by the network to an audio signal, which is computationally expensive. In this work, we apply VAEs to raw audio data directly while bypassing audio feature extraction. This approach allows the practitioners to use any audio recording while giving flexibility and control over the aesthetics through dataset curation. The lower computation time in audio signal generation allows the raw audio approach to be incorporated into real-time applications. In this work, we propose three strategies to explore latent spaces of audio and timbre for sound design applications. By doing so, our aim is to initiate a conversation on artistic approaches and strategies to utilize latent audio spaces in sound and music practices.
ML-97-标题: Fantastic DNN Classifiers and How to Identify them without Data
作者: Nathaniel Dean, Dilip Sarkar
备注: 12 pages
Abstract: Current algorithms and architecture can create excellent DNN classifier models from example data. In general, larger training datasets result in better model estimations, which improve test performance. Existing methods for predicting generalization performance are based on hold-out test examples. To the best of our knowledge, at present no method exists that can estimate the quality of a trained DNN classifier without test data. In this paper, we show that the quality of a trained DNN classifier can be assessed without any example data. We consider DNNs to be composed of a feature extractor and a feature classifier; the feature extractor’s output is fed to the classifier. The proposed method iteratively creates class prototypes in the input space for each class by minimizing a cross-entropy loss function at the output of the network. We use these prototypes and their feature relationships to reveal the quality of the classifier. We have developed two metrics: one using the features of the prototypes and the other using adversarial examples corresponding to each prototype. Empirical evaluations show that accuracy obtained from test examples is directly proportional to quality measures obtained from the proposed metrics. We report our observations for ResNet18 with Tiny ImageNet, CIFAR100, and CIFAR10 datasets. The proposed metrics can be used to compare performances of two or more classifiers without test examples.
ML-98-标题: Non-Parametric Learning of Stochastic Differential Equations with Fast Rates of Convergence
作者: Riccardo Bonalli, Alessandro Rudi
Abstract: We propose a novel non-parametric learning paradigm for the identification of drift and diffusion coefficients of non-linear stochastic differential equations, which relies upon discrete-time observations of the state. The key idea essentially consists of fitting a RKHS-based approximation of the corresponding Fokker-Planck equation to such observations, yielding theoretical estimates of learning rates which, unlike previous works, become increasingly tighter when the regularity of the unknown drift and diffusion coefficients becomes higher. Our method being kernel-based, offline pre-processing may in principle be profitably leveraged to enable efficient numerical implementation.
ML-99-标题: Deep Reinforcement Learning with Plasticity Injection
作者: Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, André Barreto
Abstract: A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered by the complex relationship between plasticity, exploration, and performance in RL. This paper introduces plasticity injection, a minimalistic intervention that increases the network plasticity without changing the number of trainable parameters or biasing the predictions. The applications of this intervention are two-fold: first, as a diagnostic tool \unicodex2014 if injection increases the performance, we may conclude that an agent’s network was losing its plasticity. This tool allows us to identify a subset of Atari environments where the lack of plasticity causes performance plateaus, motivating future studies on understanding and combating plasticity loss. Second, plasticity injection can be used to improve the computational efficiency of RL training if the agent has to re-learn from scratch due to exhausted plasticity or by growing the agent’s network dynamically without compromising performance. The results on Atari show that plasticity injection attains stronger performance compared to alternative methods while being computationally efficient.
ML-100-标题: Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
作者: Xiang Ji, Gen Li
Abstract: A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting. The existing algorithms either fail to achieve regret optimality or have to incur a high memory and computational cost. In addition, existing optimal algorithms all require a long burn-in time in order to achieve optimal sample efficiency, i.e., their optimality is not guaranteed unless sample size surpasses a high threshold. We address both open problems by introducing a model-free algorithm that employs variance reduction and a novel technique that switches the execution policy in a slow-yet-adaptive manner. This is the first regret-optimal model-free algorithm in the discounted setting, with the additional benefit of a low burn-in time.
ML-101-标题: Post-processing Private Synthetic Data for Improving Utility on Selected Measures
作者: Hao Wang, Shivchander Sudalairaj, John Henning, Kristjan Greenewald, Akash Srivastava
Abstract: Existing private synthetic data generation algorithms are agnostic to downstream tasks. However, end users may have specific requirements that the synthetic data must satisfy. Failure to meet these requirements could significantly reduce the utility of the data for downstream use. We introduce a post-processing technique that improves the utility of the synthetic data with respect to measures selected by the end user, while preserving strong privacy guarantees and dataset quality. Our technique involves resampling from the synthetic data to filter out samples that do not meet the selected utility measures, using an efficient stochastic first-order algorithm to find optimal resampling weights. Through comprehensive numerical experiments, we demonstrate that our approach consistently improves the utility of synthetic data across multiple benchmark datasets and state-of-the-art synthetic data generation algorithms.
ML-102-标题: Representation Online Matters: Practical End-to-End Diversification in Search and Recommender Systems
作者: Pedro Silva, Bhawna Juneja, Shloka Desai, Ashudeep Singh, Nadia Fawaz
备注: In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (FAccT '23), June 12–15, 2023, Chicago, IL, USA
Abstract: As the use of online platforms continues to grow across all demographics, users often express a desire to feel represented in the content. To improve representation in search results and recommendations, we introduce end-to-end diversification, ensuring that diverse content flows throughout the various stages of these systems, from retrieval to ranking. We develop, experiment, and deploy scalable diversification mechanisms in multiple production surfaces on the Pinterest platform, including Search, Related Products, and New User Homefeed, to improve the representation of different skin tones in beauty and fashion content. Diversification in production systems includes three components: identifying requests that will trigger diversification, ensuring diverse content is retrieved from the large content corpus during the retrieval stage, and finally, balancing the diversity-utility trade-off in a self-adjusting manner in the ranking stage. Our approaches, which evolved from using Strong-OR logical operator to bucketized retrieval at the retrieval stage and from greedy re-rankers to multi-objective optimization using determinantal point processes for the ranking stage, balances diversity and utility while enabling fast iterations and scalable expansion to diversification over multiple dimensions. Our experiments indicate that these approaches significantly improve diversity metrics, with a neutral to a positive impact on utility metrics and improved user satisfaction, both qualitatively and quantitatively, in production.
ML-103-标题: Editable Graph Neural Network for Node Classifications
作者: Zirui Liu, Zhimeng Jiang, Shaochen Zhong, Kaixiong Zhou, Li Li, Rui Chen, Soo-Hyun Choi, Xia Hu
Abstract: Despite Graph Neural Networks (GNNs) have achieved prominent success in many graph-based learning problem, such as credit risk assessment in financial networks and fake news detection in social networks. However, the trained GNNs still make errors and these errors may cause serious negative impact on society. \textitModel editing, which corrects the model behavior on wrongly predicted target samples while leaving model predictions unchanged on unrelated samples, has garnered significant interest in the fields of computer vision and natural language processing. However, model editing for graph neural networks (GNNs) is rarely explored, despite GNNs’ widespread applicability. To fill the gap, we first observe that existing model editing methods significantly deteriorate prediction accuracy (up to 50% accuracy drop) in GNNs while a slight accuracy drop in multi-layer perception (MLP). The rationale behind this observation is that the node aggregation in GNNs will spread the editing effect throughout the whole graph. This propagation pushes the node representation far from its original one. Motivated by this observation, we propose \underlineEditable \underlineGraph \underlineNeural \underlineNetworks (EGNN), a neighbor propagation-free approach to correct the model prediction on misclassified nodes. Specifically, EGNN simply stitches an MLP to the underlying GNNs, where the weights of GNNs are frozen during model editing. In this way, EGNN disables the propagation during editing while still utilizing the neighbor propagation scheme for node prediction to obtain satisfactory results. Experiments demonstrate that EGNN outperforms existing baselines in terms of effectiveness (correcting wrong predictions with lower accuracy drop), generalizability (correcting wrong predictions for other similar nodes), and efficiency (low training time and memory) on various graph datasets.
ML-104-标题: Improving selective classification performance of deep neural networks through post-hoc logit normalization and temperature scaling
作者: Luís Felipe P. Cattelan, Danilo Silva
Abstract: This paper addresses the problem of selective classification for deep neural networks, where a model is allowed to abstain from low-confidence predictions to avoid potential errors. Specifically, we tackle the problem of optimizing the confidence estimator of a fixed classifier, aiming to enhance its misclassification detection performance, i.e., its ability to discriminate between correct and incorrect predictions by assigning higher confidence values to the correct ones. Previous work has found that different classifiers exhibit varying levels of misclassification detection performance, particularly when using the maximum softmax probability (MSP) as a measure of confidence. However, we argue that these findings are mainly due to a sub-optimal confidence estimator being used for each model. To overcome this issue, we propose a simple and efficient post-hoc confidence estimator, named p -NormSoftmax, which consists of transforming the logits through p -norm normalization and temperature scaling, followed by taking the MSP, where p and the temperature are optimized based on a hold-out set. This estimator can be easily applied on top of an already trained model and, in many cases, can significantly improve its selective classification performance. When applied to 84 pretrained Imagenet classifiers, our method yields an average improvement of 16% in the area under the risk-coverage curve (AURC), exceeding 40% for some models. Furthermore, after applying p -NormSoftmax, we observe that these models exhibit approximately the same level of misclassification detection performance, implying that a model’s selective classification performance is almost entirely determined by its accuracy at full coverage.
ML-105-标题: Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds
作者: Harsh Sharma, Hongliang Mu, Patrick Buchfink, Rudy Geelen, Silke Glas, Boris Kramer
Abstract: This work presents two novel approaches for the symplectic model reduction of high-dimensional Hamiltonian systems using data-driven quadratic manifolds. Classical symplectic model reduction approaches employ linear symplectic subspaces for representing the high-dimensional system states in a reduced-dimensional coordinate system. While these approximations respect the symplectic nature of Hamiltonian systems, the linearity of the approximation imposes a fundamental limitation to the accuracy that can be achieved. We propose two different model reduction methods based on recently developed quadratic manifolds, each presenting its own advantages and limitations. The addition of quadratic terms in the state approximation, which sits at the heart of the proposed methodologies, enables us to better represent intrinsic low-dimensionality in the problem at hand. Both approaches are effective for issuing predictions in settings well outside the range of their training data while providing more accurate solutions than the linear symplectic reduced-order models.
ML-106-标题: SPRING: GPT -4 Out-performs RL Algorithms by Studying Papers and Reasoning
作者: Yue Wu, So Yeon Min, Shrimai Prabhumoye, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Tom Mitchell, Yuanzhi Li
Abstract: Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read the game’s original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM). Prompted with the LaTeX source as game context and a description of the agent’s current observation, our SPRING framework employs a directed acyclic graph (DAG) with game-related questions as nodes and dependencies as edges. We identify the optimal action to take in the environment by traversing the DAG and calculating LLM responses for each node in topological order, with the LLM’s answer to final node directly translating to environment actions. In our experiments, we study the quality of in-context “reasoning” induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories. Quantitatively, SPRING with GPT-4 outperforms all state-of-the-art RL baselines, trained for 1M steps, without any training. Finally, we show the potential of games as a test bed for LLMs.
ML-107-标题: Adaptive Data Analysis in a Balanced Adversarial Model
作者: Kobbi Nissim, Uri Stemmer, Eliad Tsfadia
Abstract: In adaptive data analysis, a mechanism gets n i.i.d. samples from an unknown distribution D , and is required to provide accurate estimations to a sequence of adaptively chosen statistical queries with respect to D . Hardt and Ullman (FOCS 2014) and Steinke and Ullman (COLT 2015) showed that in general, it is computationally hard to answer more than \Theta(n^2) adaptive queries, assuming the existence of one-way functions. However, these negative results strongly rely on an adversarial model that significantly advantages the adversarial analyst over the mechanism, as the analyst, who chooses the adaptive queries, also chooses the underlying distribution D . This imbalance raises questions with respect to the applicability of the obtained hardness results – an analyst who has complete knowledge of the underlying distribution D would have little need, if at all, to issue statistical queries to a mechanism which only holds a finite number of samples from D . We consider more restricted adversaries, called \emphbalanced, where each such adversary consists of two separated algorithms: The \emphsampler who is the entity that chooses the distribution and provides the samples to the mechanism, and the \emphanalyst who chooses the adaptive queries, but does not have a prior knowledge of the underlying distribution. We improve the quality of previous lower bounds by revisiting them using an efficient \emphbalanced adversary, under standard public-key cryptography assumptions. We show that these stronger hardness assumptions are unavoidable in the sense that any computationally bounded \emphbalanced adversary that has the structure of all known attacks, implies the existence of public-key cryptography.
ML-108-标题: Deep Learning-enabled MCMC for Probabilistic State Estimation in District Heating Grids
作者: Andreas Bott, Tim Janke, Florian Steinke
备注: The code for this paper is available under this https URL
Abstract: Flexible district heating grids form an important part of future, low-carbon energy systems. We examine probabilistic state estimation in such grids, i.e., we aim to estimate the posterior probability distribution over all grid state variables such as pressures, temperatures, and mass flows conditional on measurements of a subset of these states. Since the posterior state distribution does not belong to a standard class of probability distributions, we use Markov Chain Monte Carlo (MCMC) sampling in the space of network heat exchanges and evaluate the samples in the grid state space to estimate the posterior. Converting the heat exchange samples into grid states by solving the non-linear grid equations makes this approach computationally burdensome. However, we propose to speed it up by employing a deep neural network that is trained to approximate the solution of the exact but slow non-linear solver. This novel approach is shown to deliver highly accurate posterior distributions both for classic tree-shaped as well as meshed heating grids, at significantly reduced computational costs that are acceptable for online control. Our state estimation approach thus enables tightening the safety margins for temperature and pressure control and thereby a more efficient grid operation.
ML-109-标题: Exploring and Exploiting Data Heterogeneity in Recommendation
作者: Zimu Wang, Jiashuo Liu, Hao Zou, Xingxuan Zhang, Yue He, Dongxu Liang, Peng Cui
备注: 14 pages, 14 figures
Abstract: Massive amounts of data are the foundation of data-driven recommendation models. As an inherent nature of big data, data heterogeneity widely exists in real-world recommendation systems. It reflects the differences in the properties among sub-populations. Ignoring the heterogeneity in recommendation data could limit the performance of recommendation models, hurt the sub-populational robustness, and make the models misled by biases. However, data heterogeneity has not attracted substantial attention in the recommendation community. Therefore, it inspires us to adequately explore and exploit heterogeneity for solving the above problems and assisting data analysis. In this work, we focus on exploring two representative categories of heterogeneity in recommendation data that is the heterogeneity of prediction mechanism and covariate distribution and propose an algorithm that explores the heterogeneity through a bilevel clustering method. Furthermore, the uncovered heterogeneity is exploited for two purposes in recommendation scenarios which are prediction with multiple sub-models and supporting debias. Extensive experiments on real-world data validate the existence of heterogeneity in recommendation data and the effectiveness of exploring and exploiting data heterogeneity in recommendation.
ML-110-标题: Bounded Projection Matrix Approximation with Applications to Community Detection
作者: Zheng Zhai, Hengchao Chen, Qiang Sun
Abstract: Community detection is an important problem in unsupervised learning. This paper proposes to solve a projection matrix approximation problem with an additional entrywise bounded constraint. Algorithmically, we introduce a new differentiable convex penalty and derive an alternating direction method of multipliers (ADMM) algorithm. Theoretically, we establish the convergence properties of the proposed algorithm. Numerical experiments demonstrate the superiority of our algorithm over its competitors, such as the semi-definite relaxation method and spectral clustering.
ML-111-标题: Online Influence Maximization under Decreasing Cascade Model
作者: Fang Kong, Jize Xie, Baoxiang Wang, Tao Yao, Shuai Li
Abstract: We study online influence maximization (OIM) under a new model of decreasing cascade (DC). This model is a generalization of the independent cascade (IC) model by considering the common phenomenon of market saturation. In DC, the chance of an influence attempt being successful reduces with previous failures. The effect is neglected by previous OIM works under IC and linear threshold models. We propose the DC-UCB algorithm to solve this problem, which achieves a regret bound of the same order as the state-of-the-art works on the IC model. Extensive experiments on both synthetic and real datasets show the effectiveness of our algorithm.
ML-112-标题: Non-adversarial training of Neural SDEs with signature kernel scores
作者: Zacharia Issa, Blanka Horvath, Maud Lemercier, Cristopher Salvi
备注: Code available at this https URL
Abstract: Neural SDEs are continuous-time generative models for sequential data. State-of-the-art performance for irregular time series generation has been previously obtained by training these models adversarially as GANs. However, as typical for GAN architectures, training is notoriously unstable, often suffers from mode collapse, and requires specialised techniques such as weight clipping and gradient penalty to mitigate these issues. In this paper, we introduce a novel class of scoring rules on pathspace based on signature kernels and use them as objective for training Neural SDEs non-adversarially. By showing strict properness of such kernel scores and consistency of the corresponding estimators, we provide existence and uniqueness guarantees for the minimiser. With this formulation, evaluating the generator-discriminator pair amounts to solving a system of linear path-dependent PDEs which allows for memory-efficient adjoint-based backpropagation. Moreover, because the proposed kernel scores are well-defined for paths with values in infinite dimensional spaces of functions, our framework can be easily extended to generate spatiotemporal data. Our procedure permits conditioning on a rich variety of market conditions and significantly outperforms alternative ways of training Neural SDEs on a variety of tasks including the simulation of rough volatility models, the conditional probabilistic forecasts of real-world forex pairs where the conditioning variable is an observed past trajectory, and the mesh-free generation of limit order book dynamics.
ML-113-标题: Two-timescale Extragradient for Finding Local Minimax Points
作者: Jiseok Chae, Kyuwon Kim, Donghwan Kim
备注: 34 pages, 3 figures
Abstract: Minimax problems are notoriously challenging to optimize. However, we demonstrate that the two-timescale extragradient can be a viable solution. By utilizing dynamical systems theory, we show that it converges to points that satisfy the second-order necessary condition of local minimax points, under a mild condition. This work surpasses all previous results as we eliminate a crucial assumption that the Hessian, with respect to the maximization variable, is nondegenerate.
ML-114-标题: Topological gap protocol based machine learning optimization of Majorana hybrid wires
作者: Matthias Thamm, Bernd Rosenow
备注: 13 pages, 11 figures
Abstract: Majorana zero modes in superconductor-nanowire hybrid structures are a promising candidate for topologically protected qubits with the potential to be used in scalable structures. Currently, disorder in such Majorana wires is a major challenge, as it can destroy the topological phase and thus reduce the yield in the fabrication of Majorana devices. We study machine learning optimization of a gate array in proximity to a grounded Majorana wire, which allows us to reliably compensate even strong disorder. We propose a metric for optimization that is inspired by the topological gap protocol, and which can be implemented based on measurements of the non-local conductance through the wire.
ML-115-标题: Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties
作者: David Martínez-Rubio, Christophe Roux, Christopher Criscitiello, Sebastian Pokutta
Abstract: In this work, we study optimization problems of the form \min_x \max_y f(x, y) , where f(x, y) is defined on a product Riemannian manifold \mathcalM \times \mathcalN and is \mu_x -strongly geodesically convex (g-convex) in x and \mu_y -strongly g-concave in y , for \mu_x, \mu_y \geq 0 . We design accelerated methods when f is (L_x, L_y, L_xy) -smooth and \mathcalM , \mathcalN are Hadamard. To that aim we introduce new g-convex optimization results, of independent interest: we show global linear convergence for metric-projected Riemannian gradient descent and improve existing accelerated methods by reducing geometric constants. Additionally, we complete the analysis of two previous works applying to the Riemannian min-max case by removing an assumption about iterates staying in a pre-specified compact set.
ML-116-标题: Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design
作者: Jeff Guo, Philippe Schwaller
Abstract: Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal oracle evaluations (computational prediction or wet-lab experiment). This problem becomes more apparent when using oracles that can provide increased predictive accuracy but impose a significant cost. Consequently, these oracles cannot be directly optimized under a practical budget. Molecular generative models have shown remarkable sample efficiency when coupled with reinforcement learning, as demonstrated in the Practical Molecular Optimization (PMO) benchmark. Here, we propose a novel algorithm called Augmented Memory that combines data augmentation with experience replay. We show that scores obtained from oracle calls can be reused to update the model multiple times. We compare Augmented Memory to previously proposed algorithms and show significantly enhanced sample efficiency in an exploitation task and a drug discovery case study requiring both exploration and exploitation. Our method achieves a new state-of-the-art in the PMO benchmark which enforces a computational budget, outperforming the previous best performing method on 19/23 tasks.
ML-117-标题: An varepsilon-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
作者: Marc Jourdan, Rémy Degenne, Emilie Kaufmann
备注: 68 pages, 14 figures, 4 tables
Abstract: We propose EB-TC \varepsilon , a novel sampling rule for \varepsilon -best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for approximate best arm identification. EB-TC \varepsilon is an anytime sampling rule that can therefore be employed without modification for fixed confidence or fixed budget identification (without prior knowledge of the budget). We provide three types of theoretical guarantees for EB-TC \varepsilon . First, we prove bounds on its expected sample complexity in the fixed confidence setting, notably showing its asymptotic optimality in combination with an adaptive tuning of its exploration parameter. We complement these findings with upper bounds on its probability of error at any time and for any error parameter, which further yield upper bounds on its simple regret at any time. Finally, we show through numerical simulations that EB-TC \varepsilon performs favorably compared to existing algorithms, in different settings.
ML-118-标题: How many samples are needed to leverage smoothness?
作者: Vivien Cabannes, Stefano Vigogna
备注: 35 pages, 13 figures
Abstract: A core principle in statistical learning is that smoothness of target functions allows to break the curse of dimensionality. However, learning a smooth function through Taylor expansions requires enough samples close to one another to get meaningful estimate of high-order derivatives, which seems hard in machine learning problems where the ratio between number of data and input dimension is relatively small. Should we really hope to break the curse of dimensionality based on Taylor expansion estimation? What happens if Taylor expansions are replaced by Fourier or wavelet expansions? By deriving a new lower bound on the generalization error, this paper investigates the role of constants and transitory regimes which are usually not depicted beyond classical learning theory statements while that play a dominant role in practice.
ML-119-标题: PINNslope: seismic data interpolation and local slope estimation with physics informed neural networks
作者: Francesco Brandolin, Matteo Ravasi, Tariq Alkhalifah
Abstract: Interpolation of aliased seismic data constitutes a key step in a seismic processing workflow to obtain high quality velocity models and seismic images. Leveraging on the idea of describing seismic wavefields as a superposition of local plane waves, we propose to interpolate seismic data by utilizing a physics informed neural network (PINN). In the proposed framework, two feed-forward neural networks are jointly trained using the local plane wave differential equation as well as the available data as two terms in the objective function: a primary network assisted by positional encoding is tasked with reconstructing the seismic data, whilst an auxiliary, smaller network estimates the associated local slopes. Results on synthetic and field data validate the effectiveness of the proposed method in handling aliased (sampled coarsely) data and data with large gaps. Our method compares favorably against a classic least-squares inversion approach regularized by the local plane-wave equation as well as a PINN-based approach with a single network and pre-computed local slopes. We find that by introducing a second network to estimate the local slopes whilst at the same time interpolating the aliased data, the overall reconstruction capabilities and convergence behavior of the primary network is enhanced. An additional positional encoding, embedded as a network layer, confers to the network the ability to converge faster improving the accuracy of the data term.
ML-120-标题: Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms
作者: Tim Tsz-Kit Lau, Han Liu, Thomas Pock
Abstract: We study the problem of approximate sampling from non-log-concave distributions, e.g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodality. We focus on performing this task via Markov chain Monte Carlo (MCMC) methods derived from discretizations of the overdamped Langevin diffusions, which are commonly known as Langevin Monte Carlo algorithms. Furthermore, we are also interested in two nonsmooth cases for which a large class of proximal MCMC methods have been developed: (i) a nonsmooth prior is considered with a Gaussian mixture likelihood; (ii) a Laplacian mixture distribution. Such nonsmooth and non-log-concave sampling tasks arise from a wide range of applications to Bayesian inference and imaging inverse problems such as image deconvolution. We perform numerical simulations to compare the performance of most commonly used Langevin Monte Carlo algorithms.
ML-121-标题: First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities
作者: Aleksandr Beznosikov, Sergey Samsonov, Marina Sheshukova, Alexander Gasnikov, Alexey Naumov, Eric Moulines
备注: 47 pages, 3 algorithms, 2 tables
Abstract: This paper delves into stochastic optimization problems that involve Markovian noise. We present a unified approach for the theoretical analysis of first-order gradient methods for stochastic optimization and variational inequalities. Our approach covers scenarios for both non-convex and strongly convex minimization problems. To achieve an optimal (linear) dependence on the mixing time of the underlying noise sequence, we use the randomized batching scheme, which is based on the multilevel Monte Carlo method. Moreover, our technique allows us to eliminate the limiting assumptions of previous research on Markov noise, such as the need for a bounded domain and uniformly bounded stochastic gradients. Our extension to variational inequalities under Markovian noise is original. Additionally, we provide lower bounds that match the oracle complexity of our method in the case of strongly convex optimization problems.
ML-122-标题: On the Identifiability of Markov Switching Models
作者: Carles Balsells-Rodas, Yixin Wang, Yingzhen Li
Abstract: Identifiability of latent variable models has recently gained interest in terms of its applications to interpretability or out of distribution generalisation. In this work, we study identifiability of Markov Switching Models as a first step towards extending recent results to sequential latent variable models. We present identifiability conditions within first-order Markov dependency structures, and parametrise the transition distribution via non-linear Gaussians. Our experiments showcase the applicability of our approach for regime-dependent causal discovery and high-dimensional time series segmentation.
ML-123-标题: Learning and accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks
作者: Daniele Lanzoni, Olivier Pierre-Louis, Francesco Montalenti
备注: Main text and supplemental, 10 pages and 10 figures
Abstract: Generative Adversarial Networks (GANs) have shown immense potential in fields far from physics, such as in text and image generation. Here we use GANs to learn a prototypical stochastic process on a lattice. By suitably adding noise to the original data we succeed in bringing both the Generator and the Discriminator loss functions close to their ideal value. However, as typical for adversarial approaches, oscillations persist. This undermines model selection and the quality of the generated trajectory. We demonstrate that a suitable multi-model procedure where stochastic trajectories are advanced at each step upon randomly selecting a Generator leads to a remarkable increase in accuracy. Based on the reported findings GANs appears as a promising tool to tackle complex statistical dynamics.
ML-124-标题: Learning Robust Statistics for Simulation-based Inference under Model Misspecification
作者: Daolang Huang, Ayush Bharti, Amauri Souza, Luigi Acerbi, Samuel Kaski
Abstract: Simulation-based inference (SBI) methods such as approximate Bayesian computation (ABC), synthetic likelihood, and neural posterior estimation (NPE) rely on simulating statistics to infer parameters of intractable likelihood models. However, such methods are known to yield untrustworthy and misleading inference outcomes under model misspecification, thus hindering their widespread applicability. In this work, we propose the first general approach to handle model misspecification that works across different classes of SBI methods. Leveraging the fact that the choice of statistics determines the degree of misspecification in SBI, we introduce a regularized loss function that penalises those statistics that increase the mismatch between the data and the model. Taking NPE and ABC as use cases, we demonstrate the superior performance of our method on high-dimensional time-series models that are artificially misspecified. We also apply our method to real data from the field of radio propagation where the model is known to be misspecified. We show empirically that the method yields robust inference in misspecified scenarios, whilst still being accurate when the model is well-specified.
ML-125-标题: On sampling determinantal and Pfaffian point processes on a quantum computer
作者: Rémi Bardenet, Michaël Fanuel, Alexandre Feller
备注: 45 pages, 8 figures
Abstract: DPPs were introduced by Macchi as a model in quantum optics the 1970s. Since then, they have been widely used as models and subsampling tools in statistics and computer science. Most applications require sampling from a DPP, and given their quantum origin, it is natural to wonder whether sampling a DPP on a quantum computer is easier than on a classical one. We focus here on DPPs over a finite state space, which are distributions over the subsets of \1,\dots,N\ parametrized by an N\times N Hermitian kernel matrix. Vanilla sampling consists in two steps, of respective costs \mathcalO(N^3) and \mathcalO(Nr^2) operations on a classical computer, where r is the rank of the kernel matrix. A large first part of the current paper consists in explaining why the state-of-the-art in quantum simulation of fermionic systems already yields quantum DPP sampling algorithms. We then modify existing quantum circuits, and discuss their insertion in a full DPP sampling pipeline that starts from practical kernel specifications. The bottom line is that, with P (classical) parallel processors, we can divide the preprocessing cost by P and build a quantum circuit with \mathcalO(Nr) gates that sample a given DPP, with depth varying from \mathcalO(N) to \mathcalO(r\log N) depending on qubit-communication constraints on the target machine. We also connect existing work on the simulation of superconductors to Pfaffian point processes, which generalize DPPs and would be a natural addition to the machine learner’s toolbox. Finally, the circuits are empirically validated on a classical simulator and on 5-qubit machines.
ML-126-标题: Embeddings between Barron spaces with higher order activation functions
作者: Tjeerd Jan Heeringa, Len Spek, Felix Schwenninger, Christoph Brune
备注: 21 pages, 1 figure
Abstract: The approximation properties of infinitely wide shallow neural networks heavily depend on the choice of the activation function. To understand this influence, we study embeddings between Barron spaces with different activation functions. These embeddings are proven by providing push-forward maps on the measures \mu used to represent functions f . An activation function of particular interest is the rectified power unit ( \operatornameRePU ) given by \operatornameRePU_s(x)=\max(0,x)^s . For many commonly used activation functions, the well-known Taylor remainder theorem can be used to construct a push-forward map, which allows us to prove the embedding of the associated Barron space into a Barron space with a \operatornameRePU as activation function. Moreover, the Barron spaces associated with the \operatornameRePU_s have a hierarchical structure similar to the Sobolev spaces H^m .
ML-127-标题: Market Making with Deep Reinforcement Learning from Limit Order Books
作者: Hong Guo, Jianwu Lin, Fanlin Huang
Abstract: Market making (MM) is an important research topic in quantitative finance, the agent needs to continuously optimize ask and bid quotes to provide liquidity and make profits. The limit order book (LOB) contains information on all active limit orders, which is an essential basis for decision-making. The modeling of evolving, high-dimensional and low signal-to-noise ratio LOB data is a critical challenge. Traditional MM strategy relied on strong assumptions such as price process, order arrival process, etc. Previous reinforcement learning (RL) works handcrafted market features, which is insufficient to represent the market. This paper proposes a RL agent for market making with LOB data. We leverage a neural network with convolutional filters and attention mechanism (Attn-LOB) for feature extraction from LOB. We design a new continuous action space and a hybrid reward function for the MM task. Finally, we conduct comprehensive experiments on latency and interpretability, showing that our agent has good applicability.
ML-128-标题: Small Total-Cost Constraints in Contextual Bandits with Knapsacks with Application to Fairness
作者: Evgenii Chzhen (LMO, CELESTE), Christophe Giraud (LMO, CELESTE), Zhen Li, Gilles Stoltz (LMO, CELESTE, HEC Paris)
Abstract: We consider contextual bandit problems with knapsacks [CBwK], a problem where at each round, a scalar reward is obtained and vector-valued costs are suffered. The learner aims to maximize the cumulative rewards while ensuring that the cumulative costs are lower than some predetermined cost constraints. We assume that contexts come from a continuous set, that costs can be signed, and that the expected reward and cost functions, while unknown, may be uniformly estimated – a typical assumption in the literature. In this setting, total cost constraints had so far to be at least of order T^3/4 , where T is the number of rounds, and were even typically assumed to depend linearly on T . We are however motivated to use CBwK to impose a fairness constraint of equalized average costs between groups: the budget associated with the corresponding cost constraints should be as close as possible to the natural deviations, of order \sqrtT . To that end, we introduce a dual strategy based on projected-gradient-descent updates, that is able to deal with total-cost constraints of the order of \sqrtT up to poly-logarithmic terms. This strategy is more direct and simpler than existing strategies in the literature. It relies on a careful, adaptive, tuning of the step size.
ML-129-标题: Differentially Private Latent Diffusion Models
作者: Saiyue Lyu, Margarita Vinaroz, Michael F. Liu, Mijung Park
Abstract: Diffusion models (DMs) are widely used for generating high-quality image datasets. However, since they operate directly in the high-dimensional pixel space, optimization of DMs is computationally expensive, requiring long training times. This contributes to large amounts of noise being injected into the differentially private learning process, due to the composability property of differential privacy. To address this challenge, we propose training Latent Diffusion Models (LDMs) with differential privacy. LDMs use powerful pre-trained autoencoders to reduce the high-dimensional pixel space to a much lower-dimensional latent space, making training DMs more efficient and fast. Unlike [Ghalebikesabi et al., 2023] that pre-trains DMs with public data then fine-tunes them with private data, we fine-tune only the attention modules of LDMs at varying layers with privacy-sensitive data, reducing the number of trainable parameters by approximately 96% compared to fine-tuning the entire DM. We test our algorithm on several public-private data pairs, such as ImageNet as public data and CIFAR10 and CelebA as private data, and SVHN as public data and MNIST as private data. Our approach provides a promising direction for training more powerful, yet training-efficient differentially private DMs that can produce high-quality synthetic images.
ML-130-标题: Assessing the Spatial Structure of the Association between Attendance at Preschool and Childrens Developmental Vulnerabilities in Queensland Australia
作者: wala Draidi Areed, Aiden Price, Kathryn Arnett, Helen Thompson, Reid Malseed, Kerrie Mengersen
Abstract: The research explores the influence of preschool attendance (one year before full-time school) on the development of children during their first year of school. Using data collected by the Australian Early Development Census, the findings show that areas with high proportions of preschool attendance tended to have lower proportions of children with at least one developmental vulnerability. Developmental vulnerablities include not being able to cope with the school day (tired, hungry, low energy), unable to get along with others or aggressive behaviour, trouble with reading/writing or numbers. These findings, of course, vary by region. Using Data Analysis and Machine Learning, the researchers were able to identify three distinct clusters within Queensland, each characterised by different socio-demographic variables influencing the relationship between preschool attendance and developmental vulnerability. These analyses contribute to understanding regions with high vulnerability and the potential need for tailored policies or investments
ML-131-标题: Counterfactual Generative Models for Time-Varying Treatments
作者: Shenghao Wu, Wenbin Zhou, Minshuo Chen, Shixiang Zhu
Abstract: Estimating average causal effects is a common practice to test new treatments. However, the average effect ‘‘masks’’ important individual characteristics in the counterfactual distribution, which may lead to safety, fairness, and ethical concerns. This issue is exacerbated in the temporal setting, where the treatment is sequential and time-varying, leading to an intricate influence on the counterfactual distribution. In this paper, we propose a novel conditional generative modeling approach to capture the whole counterfactual distribution, allowing efficient inference on certain statistics of the counterfactual distribution. This makes the proposed approach particularly suitable for healthcare and public policy making. Our generative modeling approach carefully tackles the distribution mismatch in the observed data and the targeted counterfactual distribution via a marginal structural model. Our method outperforms state-of-the-art baselines on both synthetic and real data.
ML-132-标题: Interpretable Machine Learning based on Functional ANOVA Framework: Algorithms and Comparisons
作者: Linwei Hu, Vijayan N. Nair, Agus Sudjianto, Aijun Zhang, Jie Chen
备注: 24 pages, 15 figures. arXiv admin note: substantial text overlap with arXiv:2207.06950
Abstract: In the early days of machine learning (ML), the emphasis was on developing complex algorithms to achieve best predictive performance. To understand and explain the model results, one had to rely on post hoc explainability techniques, which are known to have limitations. Recently, with the recognition that interpretability is just as important, researchers are compromising on small increases in predictive performance to develop algorithms that are inherently interpretable. While doing so, the ML community has rediscovered the use of low-order functional ANOVA (fANOVA) models that have been known in the statistical literature for some time. This paper starts with a description of challenges with post hoc explainability and reviews the fANOVA framework with a focus on main effects and second-order interactions. This is followed by an overview of two recently developed techniques: Explainable Boosting Machines or EBM (Lou et al., 2013) and GAMI-Net (Yang et al., 2021b). The paper proposes a new algorithm, called GAMI-Lin-T, that also uses trees like EBM, but it does linear fits instead of piecewise constants within the partitions. There are many other differences, including the development of a new interaction filtering algorithm. Finally, the paper uses simulated and real datasets to compare selected ML algorithms. The results show that GAMI-Lin-T and GAMI-Net have comparable performances, and both are generally better than EBM.
ML-133-标题: Variational Gradient Descent using Local Linear Models
作者: Song Liu, Jack Simons, Mingxuan Yi, Mark Beaumont
Abstract: Stein Variational Gradient Descent (SVGD) can transport particles along trajectories that reduce the KL divergence between the target and particle distribution but requires the target score function to compute the update. We introduce a new perspective on SVGD that views it as a local estimator of the reversed KL gradient flow. This perspective inspires us to propose new estimators that use local linear models to achieve the same purpose. The proposed estimators can be computed using only samples from the target and particle distribution without needing the target score function. Our proposed variational gradient estimators utilize local linear models, resulting in computational simplicity while maintaining effectiveness comparable to SVGD in terms of estimation biases. Additionally, we demonstrate that under a mild assumption, the estimation of high-dimensional gradient flow can be translated into a lower-dimensional estimation problem, leading to improved estimation accuracy. We validate our claims with experiments on both simulated and real-world datasets.
ML-134-标题: Deep Stochastic Processes via Functional Markov Transition Operators
作者: Jin Xu, Emilien Dupont, Kaspar Märtens, Tom Rainforth, Yee Whye Teh
备注: 18 pages, 5 figures
Abstract: We introduce Markov Neural Processes (MNPs), a new class of Stochastic Processes (SPs) which are constructed by stacking sequences of neural parameterised Markov transition operators in function space. We prove that these Markov transition operators can preserve the exchangeability and consistency of SPs. Therefore, the proposed iterative construction adds substantial flexibility and expressivity to the original framework of Neural Processes (NPs) without compromising consistency or adding restrictions. Our experiments demonstrate clear advantages of MNPs over baseline models on a variety of tasks.
ML-135-标题: Online Optimization for Randomized Network Resource Allocation with Long-Term Constraints
作者: Ahmed Sid-Ali, Ioannis Lambadaris, Yiqiang Q. Zhao, Gennady Shaikhet, Shima Kheradmand
Abstract: In this paper, we study an optimal online resource reservation problem in a simple communication network. The network is composed of two compute nodes linked by a local communication link. The system operates in discrete time; at each time slot, the administrator reserves resources for servers before the actual job requests are known. A cost is incurred for the reservations made. Then, after the client requests are observed, jobs may be transferred from one server to the other to best accommodate the demands by incurring an additional transport cost. If certain job requests cannot be satisfied, there is a violation that engenders a cost to pay for each of the blocked jobs. The goal is to minimize the overall reservation cost over finite horizons while maintaining the cumulative violation and transport costs under a certain budget limit. To study this problem, we first formalize it as a repeated game against nature where the reservations are drawn randomly according to a sequence of probability distributions that are derived from an online optimization problem over the space of allowable reservations. We then propose an online saddle-point algorithm for which we present an upper bound for the associated K-benchmark regret together with an upper bound for the cumulative constraint violations. Finally, we present numerical experiments where we compare the performance of our algorithm with those of simple deterministic resource allocation policies.
ML-136-标题: RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models
作者: David Qiu, David Rim, Shaojin Ding, Oleg Rybakov, Yanzhang He
Abstract: With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models. Despite recent advances in quantization aware training (QAT) technique, most papers present evaluations that are focused on computer vision tasks, which have different training dynamics compared to sequence tasks. In this paper, we first benchmark the impact of popular techniques such as straight through estimator, pseudo-quantization noise, learnable scale parameter, clipping, etc. on 4-bit seq2seq models across a suite of speech recognition datasets ranging from 1,000 hours to 1 million hours, as well as one machine translation dataset to illustrate its applicability outside of speech. Through the experiments, we report that noise based QAT suffers when there is insufficient regularization signal flowing back to the quantization scale. We propose low complexity changes to the QAT process to improve model accuracy (outperforming popular learnable scale and clipping methods). With the improved accuracy, it opens up the possibility to exploit some of the other benefits of noise based QAT: 1) training a single model that performs well in mixed precision mode and 2) improved generalization on long form speech recognition.
ML-137-标题: Improving few-shot learning-based protein engineering with evolutionary sampling
作者: M. Zaki Jawaid, Robin W. Yeo, Aayushma Gautam, T. Blair Gainous, Daniel O. Hart, Timothy P. Daley
Abstract: Designing novel functional proteins remains a slow and expensive process due to a variety of protein engineering challenges; in particular, the number of protein variants that can be experimentally tested in a given assay pales in comparison to the vastness of the overall sequence space, resulting in low hit rates and expensive wet lab testing cycles. In this paper, we propose a few-shot learning approach to novel protein design that aims to accelerate the expensive wet lab testing cycle and is capable of leveraging a training dataset that is both small and skewed ( \approx 10^5 datapoints, < 1% positive hits). Our approach is composed of two parts: a semi-supervised transfer learning approach to generate a discrete fitness landscape for a desired protein function and a novel evolutionary Monte Carlo Markov Chain sampling algorithm to more efficiently explore the fitness landscape. We demonstrate the performance of our approach by experimentally screening predicted high fitness gene activators, resulting in a dramatically improved hit rate compared to existing methods. Our method can be easily adapted to other protein engineering and design problems, particularly where the cost associated with obtaining labeled data is significantly high. We have provided open source code for our method at https:// this http URL.
ML-138-标题: PulseNet: Deep Learning ECG-signal classification using random augmentation policy and continous wavelet transform for canines
作者: Andre Dourson, Roberto Santilli, Federica Marchesotti, Jennifer Schneiderman, Oliver Roman Stiel, Fernando Junior, Michael Fitzke, Norbert Sithirangathan, Emil Walleser, Xiaoli Qiao, Mark Parkinson
Abstract: Evaluating canine electrocardiograms (ECG) require skilled veterinarians, but current availability of veterinary cardiologists for ECG interpretation and diagnostic support is limited. Developing tools for automated assessment of ECG sequences can improve veterinary care by providing clinicians real-time results and decision support tools. We implement a deep convolutional neural network (CNN) approach for classifying canine electrocardiogram sequences as either normal or abnormal. ECG records are converted into 8 second Lead II sequences and classified as either normal (no evidence of cardiac abnormalities) or abnormal (presence of one or more cardiac abnormalities). For training ECG sequences are randomly augmented using RandomAugmentECG, a new augmentation library implemented specifically for this project. Each chunk is then is converted using a continuous wavelet transform into a 2D scalogram. The 2D scalogram are then classified as either normal or abnormal by a binary CNN classifier. Experimental results are validated against three boarded veterinary cardiologists achieving an AUC-ROC score of 0.9506 on test dataset matching human level performance. Additionally, we describe model deployment to Microsoft Azure using an MLOps approach. To our knowledge, this work is one of the first attempts to implement a deep learning model to automatically classify ECG sequences for canines.Implementing automated ECG classification will enhance veterinary care through improved diagnostic performance and increased clinic efficiency.
ML-139-标题: Machine learning-assisted close-set X-ray diffraction phase identification of transition metals ICLR2023
作者: Maksim Zhdanov, Andrey Zhdanov
备注: Published at the ICLR 2023 Workshop on Machine Learning for Materials, 5 pages, 1 figure
Abstract: Machine learning has been applied to the problem of X-ray diffraction phase prediction with promising results. In this paper, we describe a method for using machine learning to predict crystal structure phases from X-ray diffraction data of transition metals and their oxides. We evaluate the performance of our method and compare the variety of its settings. Our results demonstrate that the proposed machine learning framework achieves competitive performance. This demonstrates the potential for machine learning to significantly impact the field of X-ray diffraction and crystal structure determination. Open-source implementation: this https URL.
ML-140-标题: Understanding Spoken Language Development of Children with ASD Using Pre-trained Speech Embeddings INTERSPEECH2023
作者: Anfeng Xu, Rajat Hebbar, Rimita Lahiri, Tiantian Feng, Lindsay Butler, Lue Shen, Helen Tager-Flusberg, Shrikanth Narayanan
备注: Accepted to Interspeech 2023, 5 pages
Abstract: Speech processing techniques are useful for analyzing speech and language development in children with Autism Spectrum Disorder (ASD), who are often varied and delayed in acquiring these skills. Early identification and intervention are crucial, but traditional assessment methodologies such as caregiver reports are not adequate for the requisite behavioral phenotyping. Natural Language Sample (NLS) analysis has gained attention as a promising complement. Researchers have developed benchmarks for spoken language capabilities in children with ASD, obtainable through the analysis of NLS. This paper proposes applications of speech processing technologies in support of automated assessment of children’s spoken language development by classification between child and adult speech and between speech and nonverbal vocalization in NLS, with respective F1 macro scores of 82.6% and 67.8%, underscoring the potential for accurate and scalable tools for ASD research and clinical use.
ML-141-标题: Reimagining Demand-Side Management with Mean Field Learning
作者: Bianca Marin Moreno (EDF R&D, Thoth), Margaux Brégère (SU, LPSM (UMR_8001), EDF R&D), Pierre Gaillard (Thoth), Nadia Oudjane (EDF R&D)
Abstract: Integrating renewable energy into the power grid while balancing supply and demand is a complex issue, given its intermittent nature. Demand side management (DSM) offers solutions to this challenge. We propose a new method for DSM, in particular the problem of controlling a large population of electrical devices to follow a desired consumption signal. We model it as a finite horizon Markovian mean field control problem. We develop a new algorithm, MD-MFC, which provides theoretical guarantees for convex and Lipschitz objective functions. What distinguishes MD-MFC from the existing load control literature is its effectiveness in directly solving the target tracking problem without resorting to regularization techniques on the main problem. A non-standard Bregman divergence on a mirror descent scheme allows dynamic programming to be used to obtain simple closed-form solutions. In addition, we show that general mean-field game algorithms can be applied to this problem, which expands the possibilities for addressing load control problems. We illustrate our claims with experiments on a realistic data set.
CV-0-标题: Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
作者: Shihao Zhao, Dongdong Chen, Yen-Chun Chen, Jianmin Bao, Shaozhe Hao, Lu Yuan, Kwan-Yee K. Wong
备注: Code is available at this https URL
Abstract: Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often struggle to adequately convey detailed controls, even when composed of long and complex texts. Moreover, recent studies have also shown that these models face challenges in understanding such complex texts and generating the corresponding images. Therefore, there is a growing need to enable more control modes beyond text description. In this paper, we introduce Uni-ControlNet, a novel approach that allows for the simultaneous utilization of different local controls (e.g., edge maps, depth map, segmentation masks) and global controls (e.g., CLIP image embeddings) in a flexible and composable manner within one model. Unlike existing methods, Uni-ControlNet only requires the fine-tuning of two additional adapters upon frozen pre-trained text-to-image diffusion models, eliminating the huge cost of training from scratch. Moreover, thanks to some dedicated adapter designs, Uni-ControlNet only necessitates a constant number (i.e., 2) of adapters, regardless of the number of local or global controls used. This not only reduces the fine-tuning costs and model size, making it more suitable for real-world deployment, but also facilitate composability of different conditions. Through both quantitative and qualitative comparisons, Uni-ControlNet demonstrates its superiority over existing methods in terms of controllability, generation quality and composability. Code is available at \urlthis https URL.
CV-1-标题: Eclipse: Disambiguating Illumination and Materials using Unintended Shadows
作者: Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Todd Zickler, Pratul P. Srinivasan
备注: Project page: this https URL
Abstract: Decomposing an object’s appearance into representations of its materials and the surrounding illumination is difficult, even when the object’s 3D shape is known beforehand. This problem is ill-conditioned because diffuse materials severely blur incoming light, and is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination – even from diffuse objects – by exploiting unintended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatially-varying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who inadvertently cast shadows upon it.
CV-2-标题: Image is First-order NormLinear Autoregressive
作者: Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Youzuo Lin
Abstract: This paper reveals that every image can be understood as a first-order norm+linear autoregressive process, referred to as FINOLA, where norm+linear denotes the use of normalization before the linear model. We demonstrate that images of size 256 \times 256 can be reconstructed from a compressed vector using autoregression up to a 16 \times 16 feature map, followed by upsampling and convolution. This discovery sheds light on the underlying partial differential equations (PDEs) governing the latent feature space. Additionally, we investigate the application of FINOLA for self-supervised learning through a simple masked prediction technique. By encoding a single unmasked quadrant block, we can autoregressively predict the surrounding masked region. Remarkably, this pre-trained representation proves effective for image classification and object detection tasks, even in lightweight networks, without requiring fine-tuning. The code will be made publicly available.
CV-3-标题: Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation
作者: Shilin Yan, Renrui Zhang, Ziyu Guo, Wenchao Chen, Wei Zhang, Hongyang Li, Yu Qiao, Zhongjiang He, Peng Gao
备注: Code is released at this https URL
Abstract: Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +4.2% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at this https URL.
CV-4-标题: Making Vision Transformer s Truly Shift-Equivariant
作者: Renan A. Rojas-Gomez, Teck-Yian Lim, Minh N. Do, Raymond A. Yeh
Abstract: For computer vision tasks, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs remain sensitive to small shifts in the input image. To address this, we introduce novel designs for each of the modules in ViTs, such as tokenization, self-attention, patch merging, and positional encoding. With our proposed modules, we achieve truly shift-equivariant ViTs on four well-established models, namely, Swin, SwinV2, MViTv2, and CvT, both in theory and practice. Empirically, we tested these models on image classification and semantic segmentation, achieving competitive performance across three different datasets while maintaining 100% shift consistency.
CV-5-标题: NAP: Neural 3D Articulation Prior
作者: Jiahui Lei, Congyue Deng, Bokui Shen, Leonidas Guibas, Kostas Daniilidis
备注: project page: this https URL
Abstract: We propose Neural 3D Articulation Prior (NAP), the first 3D deep generative model to synthesize 3D articulated object models. Despite the extensive research on generating 3D objects, compositions, or scenes, there remains a lack of focus on capturing the distribution of articulated objects, a common object category for human and robot interaction. To generate articulated objects, we first design a novel articulation tree/graph parameterization and then apply a diffusion-denoising probabilistic model over this representation where articulated objects can be generated via denoising from random complete graphs. In order to capture both the geometry and the motion structure whose distribution will affect each other, we design a graph-attention denoising network for learning the reverse diffusion process. We propose a novel distance that adapts widely used 3D generation metrics to our novel task to evaluate generation quality, and experiments demonstrate our high performance in articulated object generation. We also demonstrate several conditioned generation applications, including Part2Motion, PartNet-Imagination, Motion2Part, and GAPart2Object.
CV-6-标题: Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance
作者: Congyue Deng, Jiahui Lei, Bokui Shen, Kostas Daniilidis, Leonidas Guibas
Abstract: Equivariance has gained strong interest as a desirable network property that inherently ensures robust generalization. However, when dealing with complex systems such as articulated objects or multi-object scenes, effectively capturing inter-part transformations poses a challenge, as it becomes entangled with the overall structure and local transformations. The interdependence of part assignment and per-part group action necessitates a novel equivariance formulation that allows for their co-evolution. In this paper, we present Banana, a Banach fixed-point network for equivariant segmentation with inter-part equivariance by construction. Our key insight is to iteratively solve a fixed-point problem, where point-part assignment labels and per-part SE(3)-equivariance co-evolve simultaneously. We provide theoretical derivations of both per-step equivariance and global convergence, which induces an equivariant final convergent state. Our formulation naturally provides a strict definition of inter-part equivariance that generalizes to unseen inter-part configurations. Through experiments conducted on both articulated objects and multi-object scans, we demonstrate the efficacy of our approach in achieving strong generalization under inter-part transformations, even when confronted with substantial changes in pointcloud geometry and topology.
CV-7-标题: UMat: Uncertainty-Aware Single Image High Resolution Material Capture CVPR2023
作者: Carlos Rodriguez-Pardo, Henar Dominguez-Elvira, David Pascual-Hernandez, Elena Garces
备注: CVPR 2023. Project website: this https URL
Abstract: We propose a learning-based method to recover normals, specularity, and roughness from a single diffuse image of a material, using microgeometry appearance as our primary cue. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room for generalization. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room for generalization. In contrast, in this work, we propose a novel capture approach that leverages a generative network with attention and a U-Net discriminator, which shows outstanding performance integrating global information at reduced computational complexity. We showcase the performance of our method with a real dataset of digitized textile materials and show that a commodity flatbed scanner can produce the type of diffuse illumination required as input to our method. Additionally, because the problem might be illposed -more than a single diffuse image might be needed to disambiguate the specular reflection- or because the training dataset is not representative enough of the real distribution, we propose a novel framework to quantify the model’s confidence about its prediction at test time. Our method is the first one to deal with the problem of modeling uncertainty in material digitization, increasing the trustworthiness of the process and enabling more intelligent strategies for dataset creation, as we demonstrate with an active learning experiment.
CV-8-标题: Break-A-Scene: Extracting Multiple Concepts from a Single Image
作者: Omri Avrahami, Kfir Aberman, Ohad Fried, Daniel Cohen-Or, Dani Lischinski
备注: Project page is available at: this https URL Video available at: this https URL
Abstract: Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images with variations in backgrounds and poses, and struggle when adapted to a different scenario. In this work, we introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method. Project page is available at: this https URL
CV-9-标题: Securing Deep Generative Models with Universal Adversarial Signature
作者: Yu Zeng, Mo Zhou, Yuan Xue, Vishal M. Patel
Abstract: Recent advances in deep generative models have led to the development of methods capable of synthesizing high-quality, realistic images. These models pose threats to society due to their potential misuse. Prior research attempted to mitigate these threats by detecting generated images, but the varying traces left by different generative models make it challenging to create a universal detector capable of generalizing to new, unseen generative models. In this paper, we propose to inject a universal adversarial signature into an arbitrary pre-trained generative model, in order to make its generated contents more detectable and traceable. First, the imperceptible optimal signature for each image can be found by a signature injector through adversarial training. Subsequently, the signature can be incorporated into an arbitrary generator by fine-tuning it with the images processed by the signature injector. In this way, the detector corresponding to the signature can be reused for any fine-tuned generator for tracking the generator identity. The proposed method is validated on the FFHQ and ImageNet datasets with various state-of-the-art generative models, consistently showing a promising detection rate. Code will be made publicly available at \urlthis https URL.
CV-10-标题: Imitating Task and Motion Planning with Visuomotor Transformer s
作者: Murtaza Dalal, Ajay Mandlekar, Caelan Garrett, Ankur Handa, Ruslan Salakhutdinov, Dieter Fox
Abstract: Imitation learning is a powerful tool for training robot manipulation policies, allowing them to learn from expert demonstrations without manual programming or trial-and-error. However, common methods of data collection, such as human supervision, scale poorly, as they are time-consuming and labor-intensive. In contrast, Task and Motion Planning (TAMP) can autonomously generate large-scale datasets of diverse demonstrations. In this work, we show that the combination of large-scale datasets generated by TAMP supervisors and flexible Transformer models to fit them is a powerful paradigm for robot manipulation. To that end, we present a novel imitation learning system called OPTIMUS that trains large-scale visuomotor Transformer policies by imitating a TAMP agent. OPTIMUS introduces a pipeline for generating TAMP data that is specifically curated for imitation learning and can be used to train performant transformer-based policies. In this paper, we present a thorough study of the design decisions required to imitate TAMP and demonstrate that OPTIMUS can solve a wide variety of challenging vision-based manipulation tasks with over 70 different objects, ranging from long-horizon pick-and-place tasks, to shelf and articulated object manipulation, achieving 70 to 80% success rates. Video results at this https URL
CV-11-标题: Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
作者: Zheyuan Liu, Weixuan Sun, Damien Teney, Stephen Gould
备注: 14 pages, including supplementary material
Abstract: Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these to a reference image embedding modified by the query text at test time. Such a pipeline is very efficient at test time since fast vector distances can be used to evaluate candidates, but modifying the reference image embedding guided only by a short textual description can be difficult, especially independent of potential candidates. An alternative approach is to allow interactions between the query and every possible candidate, i.e., reference-text-candidate triplets, and pick the best from the entire set. Though this approach is more discriminative, for large-scale datasets the computational cost is prohibitive since pre-computation of candidate embeddings is no longer possible. We propose to combine the merits of both schemes using a two-stage model. Our first stage adopts the conventional vector distancing metric and performs a fast pruning among candidates. Meanwhile, our second stage employs a dual-encoder architecture, which effectively attends to the input triplet of reference-text-candidate and re-ranks the candidates. Both stages utilize a vision-and-language pre-trained network, which has proven beneficial for various downstream tasks. Our method consistently outperforms state-of-the-art approaches on standard benchmarks for the task.
CV-12-标题: Look Ma No Hands! Agent-Environment Factorization of Egocentric Videos
作者: Matthew Chang, Aditya Prakash, Saurabh Gupta
备注: for project website with video, see this https URL
Abstract: The analysis and use of egocentric videos for robotic tasks is made challenging by occlusion due to the hand and the visual mismatch between the human hand and a robot end-effector. In this sense, the human hand presents a nuisance. However, often hands also provide a valuable signal, e.g. the hand pose may suggest what kind of object is being held. In this work, we propose to extract a factored representation of the scene that separates the agent (human hand) and the environment. This alleviates both occlusion and mismatch while preserving the signal, thereby easing the design of models for downstream robotics tasks. At the heart of this factorization is our proposed Video Inpainting via Diffusion Model (VIDM) that leverages both a prior on real-world images (through a large-scale pre-trained diffusion model) and the appearance of the object in earlier frames of the video (through attention). Our experiments demonstrate the effectiveness of VIDM at improving inpainting quality on egocentric videos and the power of our factored representation for numerous tasks: object detection, 3D reconstruction of manipulated objects, and learning of reward functions, policies, and affordances from videos.
CV-13-标题: HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning CVPR-23
作者: Chia-Wen Kuo, Zsolt Kira
备注: Paper accepted in CVPR-23; Project page and code available here: this https URL
Abstract: A great deal of progress has been made in image captioning, driven by research into how to encode the image using pre-trained models. This includes visual encodings (e.g. image grid features or detected objects) and more recently textual encodings (e.g. image tags or text descriptions of image regions). As more advanced encodings are available and incorporated, it is natural to ask: how to efficiently and effectively leverage the heterogeneous set of encodings? In this paper, we propose to regard the encodings as augmented views of the input image. The image captioning model encodes each view independently with a shared encoder efficiently, and a contrastive loss is incorporated across the encoded views in a novel way to improve their representation quality and the model’s data efficiency. Our proposed hierarchical decoder then adaptively weighs the encoded views according to their effectiveness for caption generation by first aggregating within each view at the token level, and then across views at the view level. We demonstrate significant performance improvements of +5.6% CIDEr on MS-COCO and +12.9% CIDEr on Flickr30k compared to state of the arts, and conduct rigorous analyses to demonstrate the importance of each part of our design.
CV-14-标题: Diversify Your Vision Dataset s with Automatic Diffusion-Based Augmentation
作者: Lisa Dunlap, Alyssa Umino, Han Zhang, Jiezhi Yang, Joseph E. Gonzalez, Trevor Darrell
Abstract: Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or location. As such, we explore how natural language descriptions of the domains seen in training data can be used with large vision models trained on diverse pretraining datasets to generate useful variations of the training data. We introduce ALIA (Automated Language-guided Image Augmentation), a method which utilizes large vision and language models to automatically generate natural language descriptions of a dataset’s domains and augment the training data via language-guided image editing. To maintain data integrity, a model trained on the original dataset filters out minimal image edits and those which corrupt class-relevant information. The resulting dataset is visually consistent with the original training data and offers significantly enhanced diversity. On fine-grained and cluttered datasets for classification and detection, ALIA surpasses traditional data augmentation and text-to-image generated data by up to 15%, often even outperforming equivalent additions of real data. Code is avilable at this https URL.
CV-15-标题: CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graphs
作者: Guangyao Zhai, Evin Pinar Örnek, Shun-Cheng Wu, Yan Di, Federico Tombari, Nassir Navab, Benjamin Busam
Abstract: Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to lacking a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset will be released upon acceptance.
CV-16-标题: CENSUS-HWR: a large training dataset for offline handwriting recognition
作者: Chetan Joshi, Lawry Sorenson, Ammon Wolfert, Dr. Mark Clement, Dr. Joseph Price, Dr. Kasey Buckles
Abstract: Progress in Automated Handwriting Recognition has been hampered by the lack of large training datasets. Nearly all research uses a set of small datasets that often cause models to overfit. We present CENSUS-HWR, a new dataset consisting of full English handwritten words in 1,812,014 gray scale images. A total of 1,865,134 handwritten texts from a vocabulary of 10,711 words in the English language are present in this collection. This dataset is intended to serve handwriting models as a benchmark for deep learning algorithms. This huge English handwriting recognition dataset has been extracted from the US 1930 and 1940 censuses taken by approximately 70,000 enumerators each year. The dataset and the trained model with their weights are freely available to download at this https URL.
CV-17-标题: UDPM: Upsampling Diffusion Probabilistic Models
作者: Shady Abu-Hussein, Raja Giryes
Abstract: In recent years, Denoising Diffusion Probabilistic Models (DDPM) have caught significant attention. By composing a Markovian process that starts in the data domain and then gradually adds noise until reaching pure white noise, they achieve superior performance in learning data distributions. Yet, these models require a large number of diffusion steps to produce aesthetically pleasing samples, which is inefficient. In addition, unlike common generative adversarial networks, the latent space of diffusion models is not interpretable. In this work, we propose to generalize the denoising diffusion process into an Upsampling Diffusion Probabilistic Model (UDPM), in which we reduce the latent variable dimension in addition to the traditional noise level addition. As a result, we are able to sample images of size 256\times 256 with only 7 diffusion steps, which is less than two orders of magnitude compared to standard DDPMs. We formally develop the Markovian diffusion processes of the UDPM, and demonstrate its generation capabilities on the popular FFHQ, LSUN horses, ImageNet, and AFHQv2 datasets. Another favorable property of UDPM is that it is very easy to interpolate its latent space, which is not the case with standard diffusion models. Our code is available online \urlthis https URL
CV-18-标题: Interactive Segment Anything NeRF with Feature Imitation
作者: Xiaokang Chen, Jiaxiang Tang, Diwen Wan, Jingbo Wang, Gang Zeng
备注: Technical Report
Abstract: This paper investigates the potential of enhancing Neural Radiance Fields (NeRF) with semantics to expand their applications. Although NeRF has been proven useful in real-world applications like VR and digital creation, the lack of semantics hinders interaction with objects in complex scenes. We propose to imitate the backbone feature of off-the-shelf perception models to achieve zero-shot semantic segmentation with NeRF. Our framework reformulates the segmentation process by directly rendering semantic features and only applying the decoder from perception models. This eliminates the need for expensive backbones and benefits 3D consistency. Furthermore, we can project the learned semantics onto extracted mesh surfaces for real-time interaction. With the state-of-the-art Segment Anything Model (SAM), our framework accelerates segmentation by 16 times with comparable mask quality. The experimental results demonstrate the efficacy and computational advantages of our approach. Project page: \urlhttps://me.kiui.moe/san/.
CV-19-标题: ProSpect: Expanded Conditioning for the Personalization of Attribute-aware Image Generation
作者: Yuxin Zhang, Weiming Dong, Fan Tang, Nisha Huang, Haibin Huang, Chongyang Ma, Tong-Yee Lee, Oliver Deussen, Changsheng Xu
Abstract: Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textual conditioning space and compose new natural sentences for text-to-image diffusion models. However, representing and editing specific visual attributes like material, style, layout, etc. remains a challenge, leading to a lack of disentanglement and editability. To address this, we propose a novel approach that leverages the step-by-step generation process of diffusion models, which generate images from low- to high-frequency information, providing a new perspective on representing, generating, and editing images. We develop Prompt Spectrum Space P*, an expanded textual conditioning space, and a new image representation method called ProSpect. ProSpect represents an image as a collection of inverted textual token embeddings encoded from per-stage prompts, where each prompt corresponds to a specific generation stage (i.e., a group of consecutive steps) of the diffusion model. Experimental results demonstrate that P* and ProSpect offer stronger disentanglement and controllability compared to existing methods. We apply ProSpect in various personalized attribute-aware image generation applications, such as image/text-guided material/style/layout transfer/editing, achieving previously unattainable results with a single image input without fine-tuning the diffusion models.
CV-20-标题: Prompt -Free Diffusion: Taking “Text” out of Text-to-Image Diffusion Models
作者: Xingqian Xu, Jiayi Guo, Zhangyang Wang, Gao Huang, Irfan Essa, Humphrey Shi
Abstract: Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. Moreover, as commonly argued: “an image is worth a thousand words” - the attempt to describe a desired image with texts often ends up being ambiguous and cannot comprehensively cover delicate visual details, hence necessitating more additional controls from the visual domain. In this paper, we take a bold step forward: taking “Text” out of a pre-trained T2I diffusion model, to reduce the burdensome prompt engineering efforts for users. Our proposed framework, Prompt-Free Diffusion, relies on only visual inputs to generate new images: it takes a reference image as “context”, an optional image structural conditioning, and an initial noise, with absolutely no text prompt. The core architecture behind the scene is Semantic Context Encoder (SeeCoder), substituting the commonly used CLIP-based or LLM-based text encoder. The reusability of SeeCoder also makes it a convenient drop-in component: one can also pre-train a SeeCoder in one T2I model and reuse it for another. Through extensive experiments, Prompt-Free Diffusion is experimentally found to (i) outperform prior exemplar-based image synthesis approaches; (ii) perform on par with state-of-the-art T2I models using prompts following the best practice; and (iii) be naturally extensible to other downstream applications such as anime figure generation and virtual try-on, with promising quality. Our code and models are open-sourced at this https URL.
CV-21-标题: On the Robustness of Segment Anything
作者: Yihao Huang, Yue Cao, Tianlin Li, Felix Juefei-Xu, Di Lin, Ivor W.Tsang, Yang Liu, Qing Guo
备注: 22 pages
Abstract: Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt (e.g., points, bounding boxes, or masks) and an input image, SAM is able to generate valid segment masks for all objects indicated by the prompts, presenting high generalization across diverse scenarios and being a general method for zero-shot transfer to downstream vision tasks. Nevertheless, it remains unclear whether SAM may introduce errors in certain threatening scenarios. Clarifying this is of significant importance for applications that require robustness, such as autonomous vehicles. In this paper, we aim to study the testing-time robustness of SAM under adversarial scenarios and common corruptions. To this end, we first build a testing-time robustness evaluation benchmark for SAM by integrating existing public datasets. Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness. Third, we study the robustness of SAM under diverse corruption types by evaluating SAM on corrupted datasets with different prompts. With experiments conducted on SA-1B and KITTI datasets, we find that SAM exhibits remarkable robustness against various corruptions, except for blur-related corruption. Furthermore, SAM remains susceptible to adversarial attacks, particularly when subjected to PGD and BIM attacks. We think such a comprehensive study could highlight the importance of the robustness issues of SAM and trigger a series of new tasks for SAM as well as downstream vision tasks.
CV-22-标题: Cross-supervised Dual Classifiers for Semi-supervised Medical Image Segmentation
作者: Zhenxi Zhang, Ran Ran, Chunna Tian, Heng Zhou, Fan Yang, Xin Li, Zhicheng Jiao
备注: 13 pages, 4 figures, 5 tables. Code will come soon
Abstract: Semi-supervised medical image segmentation offers a promising solution for large-scale medical image analysis by significantly reducing the annotation burden while achieving comparable performance. Employing this method exhibits a high degree of potential for optimizing the segmentation process and increasing its feasibility in clinical settings during translational investigations. Recently, cross-supervised training based on different co-training sub-networks has become a standard paradigm for this task. Still, the critical issues of sub-network disagreement and label-noise suppression require further attention and progress in cross-supervised training. This paper proposes a cross-supervised learning framework based on dual classifiers (DC-Net), including an evidential classifier and a vanilla classifier. The two classifiers exhibit complementary characteristics, enabling them to handle disagreement effectively and generate more robust and accurate pseudo-labels for unlabeled data. We also incorporate the uncertainty estimation from the evidential classifier into cross-supervised training to alleviate the negative effect of the error supervision signal. The extensive experiments on LA and Pancreas-CT dataset illustrate that DC-Net outperforms other state-of-the-art methods for semi-supervised segmentation. The code will be released soon.
CV-23-标题: Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image Segmentation MICCAI2023
作者: Zhenxi Zhang, Ran Ran, Chunna Tian, Heng Zhou, Xin Li, Fan Yang, Zhicheng Jiao
备注: 14 pages, Early accepted in MICCAI 2023, code will be released soon
Abstract: Consistency learning plays a crucial role in semi-supervised medical image segmentation as it enables the effective utilization of limited annotated data while leveraging the abundance of unannotated data. The effectiveness and efficiency of consistency learning are challenged by prediction diversity and training stability, which are often overlooked by existing studies. Meanwhile, the limited quantity of labeled data for training often proves inadequate for formulating intra-class compactness and inter-class discrepancy of pseudo labels. To address these issues, we propose a self-aware and cross-sample prototypical learning method (SCP-Net) to enhance the diversity of prediction in consistency learning by utilizing a broader range of semantic information derived from multiple inputs. Furthermore, we introduce a self-aware consistency learning method that exploits unlabeled data to improve the compactness of pseudo labels within each class. Moreover, a dual loss re-weighting method is integrated into the cross-sample prototypical consistency learning method to improve the reliability and stability of our model. Extensive experiments on ACDC dataset and PROMISE12 dataset validate that SCP-Net outperforms other state-of-the-art semi-supervised segmentation methods and achieves significant performance gains compared to the limited supervised training. Our code will come soon.
CV-24-标题: ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
作者: Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu
备注: Project page: this https URL
Abstract: Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and large CFG weights. In comparison, VSD works well with various CFG weights as ancestral sampling from diffusion models and simultaneously improves the diversity and sample quality with a common CFG weight (i.e., 7.5 ). We further present various improvements in the design space for text-to-3D such as distillation time schedule and density initialization, which are orthogonal to the distillation algorithm yet not well explored. Our overall approach, dubbed ProlificDreamer, can generate high rendering resolution (i.e., 512\times512 ) and high-fidelity NeRF with rich structure and complex effects (e.g., smoke and drops). Further, initialized from NeRF, meshes fine-tuned by VSD are meticulously detailed and photo-realistic. Project page: this https URL
CV-25-标题: Masked and Permuted Implicit Context Learning for Scene Text Recognition
作者: Xiaomeng Yang, Zhi Qiao, Jin Wei, Yu Zhou, Ye Yuan, Zhilong Ji, Dongbao Yang, Weiping Wang
Abstract: Scene Text Recognition (STR) is a challenging task due to variations in text style, shape, and background. Incorporating linguistic information is an effective way to enhance the robustness of STR models. Existing methods rely on permuted language modeling (PLM) or masked language modeling (MLM) to learn contextual information implicitly, either through an ensemble of permuted autoregressive (AR) LMs training or iterative non-autoregressive (NAR) decoding procedure. However, these methods exhibit limitations: PLM’s AR decoding results in the lack of information about future characters, while MLM provides global information of the entire text but neglects dependencies among each predicted character. In this paper, we propose a Masked and Permuted Implicit Context Learning Network for STR, which unifies PLM and MLM within a single decoding architecture, inheriting the advantages of both approaches. We utilize the training procedure of PLM, and to integrate MLM, we incorporate word length information into the decoding process by introducing specific numbers of mask tokens. Experimental results demonstrate that our proposed model achieves state-of-the-art performance on standard benchmarks using both AR and NAR decoding procedures.
CV-26-标题: Unifying GANs and Score-Based Diffusion as Generative Particle Models
作者: Jean-Yves Franceschi, Mike Gartrell, Ludovic Dos Santos, Thibaut Issenhuth, Emmanuel de Bézenac, Mickaël Chen, Alain Rakotomamonjy
Abstract: Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance. Their principle of displacing particle distributions by differential equations is conventionally seen as opposed to the previously widespread generative adversarial networks (GANs), which involve training a pushforward generator network. In this paper, we challenge this interpretation and propose a novel framework that unifies particle and adversarial generative models by framing generator training as a generalization of particle models. This suggests that a generator is an optional addition to any such generative model. Consequently, integrating a generator into a score-based diffusion model and training a GAN without a generator naturally emerge from our framework. We empirically test the viability of these original models as proofs of concepts of potential applications of our framework.
CV-27-标题: Domain-Adaptive Full-Face Gaze Estimation via Novel-View-Synthesis and Feature Disentanglement
作者: Jiawei Qin, Takuru Shimoyama, Xucong Zhang, Yusuke Sugano
Abstract: Along with the recent development of deep neural networks, appearance-based gaze estimation has succeeded considerably when training and testing within the same domain. Compared to the within-domain task, the variance of different domains makes the cross-domain performance drop severely, preventing gaze estimation deployment in real-world applications. Among all the factors, ranges of head pose and gaze are believed to play a significant role in the final performance of gaze estimation, while collecting large ranges of data is expensive. This work proposes an effective model training pipeline consisting of a training data synthesis and a gaze estimation model for unsupervised domain adaptation. The proposed data synthesis leverages the single-image 3D reconstruction to expand the range of the head poses from the source domain without requiring a 3D facial shape dataset. To bridge the inevitable gap between synthetic and real images, we further propose an unsupervised domain adaptation method suitable for synthetic full-face data. We propose a disentangling autoencoder network to separate gaze-related features and introduce background augmentation consistency loss to utilize the characteristics of the synthetic source domain. Through comprehensive experiments, we show that the model only using monocular-reconstructed synthetic training data can perform comparably to real data with a large label range. Our proposed domain adaptation approach further improves the performance on multiple target domains. The code and data will be available at \urlthis https URL.
CV-28-标题: Introducing Explicit Gaze Constraints to Face Swapping
作者: Ethan Wilson, Frederick Shic, Eakta Jain
备注: Published in 2023 Symposium on Eye Tracking Research and Applications (ETRA '23), May 30-June 2, 2023, Tubingen, Germany, this https URL
Abstract: Face swapping combines one face’s identity with another face’s non-appearance attributes (expression, head pose, lighting) to generate a synthetic face. This technology is rapidly improving, but falls flat when reconstructing some attributes, particularly gaze. Image-based loss metrics that consider the full face do not effectively capture the perceptually important, yet spatially small, eye regions. Improving gaze in face swaps can improve naturalness and realism, benefiting applications in entertainment, human computer interaction, and more. Improved gaze will also directly improve Deepfake detection efforts, serving as ideal training data for classifiers that rely on gaze for classification. We propose a novel loss function that leverages gaze prediction to inform the face swap model during training and compare against existing methods. We find all methods to significantly benefit gaze in resulting face swaps.
CV-29-标题: OVO: Open-Vocabulary Occupancy
作者: Zhiyu Tan, Zichao Dong, Cheng Zhang, Weikun Zhang, Hang Ji, Hao Li
Abstract: Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment. Existing occupancy prediction methods are almost entirely trained on human-annotated volumetric data. Although of high quality, the generation of such 3D annotations is laborious and costly, restricting them to a few specific object categories in the training dataset. To address this limitation, this paper proposes Open Vocabulary Occupancy (OVO), a novel approach that allows semantic occupancy prediction of arbitrary classes but without the need for 3D annotations during training. Keys to our approach are (1) knowledge distillation from a pre-trained 2D open-vocabulary segmentation model to the 3D occupancy network, and (2) pixel-voxel filtering for high-quality training data generation. The resulting framework is simple, compact, and compatible with most state-of-the-art semantic occupancy prediction models. On NYUv2 and SemanticKITTI datasets, OVO achieves competitive performance compared to supervised semantic occupancy prediction approaches. Furthermore, we conduct extensive analyses and ablation studies to offer insights into the design of the proposed framework.
CV-30-标题: Energy-based Detection of Adverse Weather Effects in LiDAR Data
作者: Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp, Marc Walessa, Daniel Meissner, Klaus Dietmayer
备注: Accepted for publication in IEEE Robotics and Automation Letters (RA-L)
Abstract: Autonomous vehicles rely on LiDAR sensors to perceive the environment. Adverse weather conditions like rain, snow, and fog negatively affect these sensors, reducing their reliability by introducing unwanted noise in the measurements. In this work, we tackle this problem by proposing a novel approach for detecting adverse weather effects in LiDAR data. We reformulate this problem as an outlier detection task and use an energy-based framework to detect outliers in point clouds. More specifically, our method learns to associate low energy scores with inlier points and high energy scores with outliers allowing for robust detection of adverse weather effects. In extensive experiments, we show that our method performs better in adverse weather detection and has higher robustness to unseen weather effects than previous state-of-the-art methods. Furthermore, we show how our method can be used to perform simultaneous outlier detection and semantic segmentation. Finally, to help expand the research field of LiDAR perception in adverse weather, we release the SemanticSpray dataset, which contains labeled vehicle spray data in highway-like scenarios.
CV-31-标题: Robust Category-Level 3D Pose Estimation from Synthetic Data
作者: Jiahao Yang, Wufei Ma, Angtian Wang, Xiaoding Yuan, Alan Yuille, Adam Kortylewski
Abstract: Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is time-consuming and challenging. While synthetically generated training data is a viable alternative, the domain shift between real and synthetic data is a significant challenge. In this work, we aim to narrow the performance gap between models trained on synthetic data and few real images and fully supervised models trained on large-scale data. We achieve this by approaching the problem from two perspectives: 1) We introduce SyntheticP3D, a new synthetic dataset for object pose estimation generated from CAD models and enhanced with a novel algorithm. 2) We propose a novel approach (CC3D) for training neural mesh models that perform pose estimation via inverse rendering. In particular, we exploit the spatial relationships between features on the mesh surface and a contrastive learning scheme to guide the domain adaptation process. Combined, these two approaches enable our models to perform competitively with state-of-the-art models using only 10% of the respective real training images, while outperforming the SOTA model by 10.4% with a threshold of pi/18 using only 50% of the real training data. Our trained model further demonstrates robust generalization to out-of-distribution scenarios despite being trained with minimal real data.
CV-32-标题: Guided Attention for Next Active Object @ EGO4D STA Challenge CVPR
作者: Sanket Thakur, Cigdem Beyan, Pietro Morerio, Vittorio Murino, Alessio Del Bue
备注: Winner of CVPR@2023 Ego4D STA challenge. arXiv admin note: substantial text overlap with arXiv:2305.12953
Abstract: In this technical report, we describe the Guided-Attention mechanism based solution for the short-term anticipation (STA) challenge for the EGO4D challenge. It combines the object detections, and the spatiotemporal features extracted from video clips, enhancing the motion and contextual information, and further decoding the object-centric and motion-centric information to address the problem of STA in egocentric videos. For the challenge, we build our model on top of StillFast with Guided Attention applied on fast network. Our model obtains better performance on the validation set and also achieves state-of-the-art (SOTA) results on the challenge test set for EGO4D Short-Term Object Interaction Anticipation Challenge.
CV-33-标题: CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition INTERSPEECH2023
作者: Lantian Li, Xiaolou Li, Haoyu Jiang, Chen Chen, Ruihai Hou, Dong Wang
备注: to be published in INTERSPEECH 2023
Abstract: Audio-visual person recognition (AVPR) has received extensive attention. However, most datasets used for AVPR research so far are collected in constrained environments, and thus cannot reflect the true performance of AVPR systems in real-world scenarios. To meet the request for research on AVPR in unconstrained conditions, this paper presents a multi-genre AVPR dataset collected `in the wild’, named CN-Celeb-AV. This dataset contains more than 420k video segments from 1,136 persons from public media. In particular, we put more emphasis on two real-world complexities: (1) data in multiple genres; (2) segments with partial information. A comprehensive study was conducted to compare CN-Celeb-AV with two popular public AVPR benchmark datasets, and the results demonstrated that CN-Celeb-AV is more in line with real-world scenarios and can be regarded as a new benchmark dataset for AVPR research. The dataset also involves a development set that can be used to boost the performance of AVPR systems in real-life situations. The dataset is free for researchers and can be downloaded from this http URL.
CV-34-标题: GenerateCT: Text-Guided 3D Chest CT Generation
作者: Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, Alperen Tezcan, Ayse Gulnihan Simsek, Furkan Almas, Sevval Nil Esirgun, Hadrien Reynaud, Sarthak Pati, Christian Bluethgen, Bjoern Menze
Abstract: Generative modeling has experienced substantial progress in recent years, particularly in text-to-image and text-to-video synthesis. However, the medical field has not yet fully exploited the potential of large-scale foundational models for synthetic data generation. In this paper, we introduce GenerateCT, the first method for text-conditional computed tomography (CT) generation, addressing the limitations in 3D medical imaging research and making our entire framework open-source. GenerateCT consists of a pre-trained large language model, a transformer-based text-conditional 3D chest CT generation architecture, and a text-conditional spatial super-resolution diffusion model. We also propose CT-ViT, which efficiently compresses CT volumes while preserving auto-regressiveness in-depth, enabling the generation of 3D CT volumes with variable numbers of axial slices. Our experiments demonstrate that GenerateCT can produce realistic, high-resolution, and high-fidelity 3D chest CT volumes consistent with medical language text prompts. We further investigate the potential of GenerateCT by training a model using generated CT volumes for multi-abnormality classification of chest CT volumes. Our contributions provide a valuable foundation for future research in text-conditional 3D medical image generation and have the potential to accelerate advancements in medical imaging research. Our code, pre-trained models, and generated data are available at this https URL.
CV-35-标题: Collaborative Blind Image Deblurring
作者: Thomas Eboli, Jean-Michel Morel, Gabriele Facciolo
备注: 23 pages, 14 figures
Abstract: Blurry images usually exhibit similar blur at various locations across the image domain, a property barely captured in nowadays blind deblurring neural networks. We show that when extracting patches of similar underlying blur is possible, jointly processing the stack of patches yields superior accuracy than handling them separately. Our collaborative scheme is implemented in a neural architecture with a pooling layer on the stack dimension. We present three practical patch extraction strategies for image sharpening, camera shake removal and optical aberration correction, and validate the proposed approach on both synthetic and real-world benchmarks. For each blur instance, the proposed collaborative strategy yields significant quantitative and qualitative improvements.
CV-36-标题: NVTC: Nonlinear Vector Transform Coding CVPR2023
作者: Runsen Feng, Zongyu Guo, Weiping Li, Zhibo Chen
备注: Accepted by CVPR 2023
Abstract: In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance. Recent state-of-the-art methods for neural image compression are mainly based on nonlinear transform coding (NTC) with uniform scalar quantization, overlooking the benefits of VQ due to its exponentially increased complexity. In this paper, we first investigate on some toy sources, demonstrating that even if modern neural networks considerably enhance the compression performance of SQ with nonlinear transform, there is still an insurmountable chasm between SQ and VQ. Therefore, revolving around VQ, we propose a novel framework for neural image compression named Nonlinear Vector Transform Coding (NVTC). NVTC solves the critical complexity issue of VQ through (1) a multi-stage quantization strategy and (2) nonlinear vector transforms. In addition, we apply entropy-constrained VQ in latent space to adaptively determine the quantization boundaries for joint rate-distortion optimization, which improves the performance both theoretically and experimentally. Compared to previous NTC approaches, NVTC demonstrates superior rate-distortion performance, faster decoding speed, and smaller model size. Our code is available at this https URL
CV-37-标题: Triplet Knowledge Distillation
作者: Xijun Wang, Dongyang Liu, Meina Kan, Chunrui Han, Zhongqin Wu, Shiguang Shan
Abstract: In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mimicking difficulty, we introduce a triplet knowledge distillation mechanism named TriKD. Besides teacher and student, TriKD employs a third role called anchor model. Before distillation begins, the pre-trained anchor model delimits a subspace within the full solution space of the target problem. Solutions within the subspace are expected to be easy targets that the student could mimic well. Distillation then begins in an online manner, and the teacher is only allowed to express solutions within the aforementioned subspace. Surprisingly, benefiting from accurate but easy-to-mimic hints, the student can finally perform well. After the student is well trained, it can be used as the new anchor for new students, forming a curriculum learning strategy. Our experiments on image classification and face recognition with various models clearly demonstrate the effectiveness of our method. Furthermore, the proposed TriKD is also effective in dealing with the overfitting issue. Moreover, our theoretical analysis supports the rationality of our triplet distillation.
CV-38-标题: ChatCAD: Towards a Universal and Reliable Interactive CAD using LLMs
作者: Zihao Zhao, Sheng Wang, Jinchen Gu, Yitao Zhu, Lanzhuju Mei, Zixu Zhuang, Zhiming Cui, Qian Wang, Dinggang Shen
备注: * These authors contribute equally to this work and should be considered co-first authors
Abstract: The potential of integrating Computer-Assisted Diagnosis (CAD) with Large Language Models (LLMs) in clinical applications, particularly in digital family doctor and clinic assistant roles, shows promise. However, existing works have limitations in terms of reliability, effectiveness, and their narrow applicability to specific image domains, which restricts their overall processing capabilities. Moreover, the mismatch in writing style between LLMs and radiologists undermines their practical utility. To address these challenges, we present ChatCAD+, an interactive CAD system that is universal, reliable, and capable of handling medical images from diverse domains. ChatCAD+ utilizes current information obtained from reputable medical websites to offer precise medical advice. Additionally, it incorporates a template retrieval system that emulates real-world diagnostic reporting, thereby improving its seamless integration into existing clinical workflows. The source code is available at \hrefthis https URLGitHub. The online demo will be available soon.
CV-39-标题: DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification
作者: Sitian Shen, Zilin Zhu, Linqian Fan, Harry Zhang, Xinxiao Wu
Abstract: Large pre-trained models have had a significant impact on computer vision by enabling multi-modal learning, where the CLIP model has achieved impressive results in image classification, object detection, and semantic segmentation. However, the model’s performance on 3D point cloud processing tasks is limited due to the domain gap between depth maps from 3D projection and training images of CLIP. This paper proposes DiffCLIP, a new pre-training framework that incorporates stable diffusion with ControlNet to minimize the domain gap in the visual branch. Additionally, a style-prompt generation module is introduced for few-shot tasks in the textual branch. Extensive experiments on the ModelNet10, ModelNet40, and ScanObjectNN datasets show that DiffCLIP has strong abilities for 3D understanding. By using stable diffusion and style-prompt generation, DiffCLIP achieves an accuracy of 43.2% for zero-shot classification on OBJ_BG of ScanObjectNN, which is state-of-the-art performance, and an accuracy of 80.6% for zero-shot classification on ModelNet10, which is comparable to state-of-the-art performance.
CV-40-标题: Anomaly Detection with Conditioned Denoising Diffusion Models
作者: Arian Mousakhan, Thomas Brox, Jawad Tayyub
Abstract: Reconstruction-based methods have struggled to achieve competitive performance on anomaly detection. In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD). We propose a novel denoising process for image reconstruction conditioned on a target image. This results in a coherent restoration that closely resembles the target image. Subsequently, our anomaly detection framework leverages this conditioning where the target image is set as the input image to guide the denoising process, leading to defectless reconstruction while maintaining nominal patterns. We localise anomalies via a pixel-wise and feature-wise comparison of the input and reconstructed image. Finally, to enhance the effectiveness of feature comparison, we introduce a domain adaptation method that utilises generated examples from our conditioned denoising process to fine-tune the feature extractor. The veracity of the approach is demonstrated on various datasets including MVTec and VisA benchmarks, achieving state-of-the-art results of 99.5% and 99.3% image-level AUROC respectively.
CV-41-标题: Comparison of Pedestrian Prediction Models from Trajectory and Appearance Data for Autonomous Driving
作者: Anthony Knittel, Morris Antonello, John Redford, Subramanian Ramamoorthy
Abstract: The ability to anticipate pedestrian motion changes is a critical capability for autonomous vehicles. In urban environments, pedestrians may enter the road area and create a high risk for driving, and it is important to identify these cases. Typical predictors use the trajectory history to predict future motion, however in cases of motion initiation, motion in the trajectory may only be clearly visible after a delay, which can result in the pedestrian has entered the road area before an accurate prediction can be made. Appearance data includes useful information such as changes of gait, which are early indicators of motion changes, and can inform trajectory prediction. This work presents a comparative evaluation of trajectory-only and appearance-based methods for pedestrian prediction, and introduces a new dataset experiment for prediction using appearance. We create two trajectory and image datasets based on the combination of image and trajectory sequences from the popular NuScenes dataset, and examine prediction of trajectories using observed appearance to influence futures. This shows some advantages over trajectory prediction alone, although problems with the dataset prevent advantages of appearance-based models from being shown. We describe methods for improving the dataset and experiment to allow benefits of appearance-based models to be captured.
CV-42-标题: Mask Attack Detection Using Vascular-weighted Motion-robust rPPG Signals
作者: Chenglin Yao, Jianfeng Ren, Ruibin Bai, Heshan Du, Jiang Liu, Xudong Jiang
Abstract: Detecting 3D mask attacks to a face recognition system is challenging. Although genuine faces and 3D face masks show significantly different remote photoplethysmography (rPPG) signals, rPPG-based face anti-spoofing methods often suffer from performance degradation due to unstable face alignment in the video sequence and weak rPPG signals. To enhance the rPPG signal in a motion-robust way, a landmark-anchored face stitching method is proposed to align the faces robustly and precisely at the pixel-wise level by using both SIFT keypoints and facial landmarks. To better encode the rPPG signal, a weighted spatial-temporal representation is proposed, which emphasizes the face regions with rich blood vessels. In addition, characteristics of rPPG signals in different color spaces are jointly utilized. To improve the generalization capability, a lightweight EfficientNet with a Gated Recurrent Unit (GRU) is designed to extract both spatial and temporal features from the rPPG spatial-temporal representation for classification. The proposed method is compared with the state-of-the-art methods on five benchmark datasets under both intra-dataset and cross-dataset evaluations. The proposed method shows a significant and consistent improvement in performance over other state-of-the-art rPPG-based methods for face spoofing detection.
CV-43-标题: Camera-Incremental Object Re-Identification with Id entity Knowledge Evolution
作者: Hantao Yao, Lu Yu, Jifei Luo, Changsheng Xu
Abstract: Object Re-identification (ReID) aims to retrieve the probe object from many gallery images with the ReID model inferred based on a stationary camera-free dataset by associating and collecting the identities across all camera views. When deploying the ReID algorithm in real-world scenarios, the aspect of storage, privacy constraints, and dynamic changes of cameras would degrade its generalizability and applicability. Treating each camera’s data independently, we introduce a novel ReID task named Camera-Incremental Object Re-identification (CIOR) by continually optimizing the ReID mode from the incoming stream of the camera dataset. Since the identities under different camera views might describe the same object, associating and distilling the knowledge of common identities would boost the discrimination and benefit from alleviating the catastrophic forgetting. In this paper, we propose a novel Identity Knowledge Evolution (IKE) framework for CIOR, consisting of the Identity Knowledge Association (IKA), Identity Knowledge Distillation (IKD), and Identity Knowledge Update (IKU). IKA is proposed to discover the common identities between the current identity and historical identities. IKD has applied to distillate historical identity knowledge from common identities and quickly adapt the historical model to the current camera view. After each camera has been trained, IKU is applied to continually expand the identity knowledge by combining the historical and current identity memories. The evaluation of Market-CL and Veri-CL shows the Identity Knowledge Evolution (IKE) effectiveness for CIOR. code:this https URL
CV-44-标题: MixFormerV2: Efficient Fully Transformer Tracking
作者: Yutao Cui, Tianhui Song, Gangshan Wu, Limin Wang
Abstract: Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a fully transformer tracking framework, coined as \emphMixFormerV2, without any dense convolutional operation and complex score prediction module. Our key design is to introduce four special prediction tokens and concatenate them with the tokens from target template and search areas. Then, we apply the unified transformer backbone on these mixed token sequence. These prediction tokens are able to capture the complex correlation between target template and search area via mixed attentions. Based on them, we can easily predict the tracking box and estimate its confidence score through simple MLP heads. To further improve the efficiency of MixFormerV2, we present a new distillation-based model reduction paradigm, including dense-to-sparse distillation and deep-to-shallow distillation. The former one aims to transfer knowledge from the dense-head based MixViT to our fully transformer tracker, while the latter one is used to prune some layers of the backbone. We instantiate two types of MixForemrV2, where the MixFormerV2-B achieves an AUC of 70.6% on LaSOT and an AUC of 57.4% on TNL2k with a high GPU speed of 165 FPS, and the MixFormerV2-S surpasses FEAR-L by 2.7% AUC on LaSOT with a real-time CPU speed.
CV-45-标题: RC-BEVFusion: A Plug-In Module for Radar-Camera Birds Eye View Feature Fusion
作者: Lukas Stäcker, Shashank Mishra, Philipp Heidenreich, Jason Rambach, Didier Stricker
Abstract: Radars and cameras belong to the most frequently used sensors for advanced driver assistance systems and automated driving research. However, there has been surprisingly little research on radar-camera fusion with neural networks. One of the reasons is a lack of large-scale automotive datasets with radar and unmasked camera data, with the exception of the nuScenes dataset. Another reason is the difficulty of effectively fusing the sparse radar point cloud on the bird’s eye view (BEV) plane with the dense images on the perspective plane. The recent trend of camera-based 3D object detection using BEV features has enabled a new type of fusion, which is better suited for radars. In this work, we present RC-BEVFusion, a modular radar-camera fusion network on the BEV plane. We propose BEVFeatureNet, a novel radar encoder branch, and show that it can be incorporated into several state-of-the-art camera-based architectures. We show significant performance gains of up to 28% increase in the nuScenes detection score, which is an important step in radar-camera fusion research. Without tuning our model for the nuScenes benchmark, we achieve the best result among all published methods in the radar-camera fusion category.
CV-46-标题: Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
作者: Tsu-Ching Hsiao, Hao-Wei Chen, Hsuan-Kung Yang, Chun-Yi Lee
Abstract: Addressing accuracy limitations and pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions. In response, we introduce a novel score-based diffusion method applied to the SE(3) group, marking the first application of diffusion models to SE(3) within the image domain, specifically tailored for pose estimation tasks. Extensive evaluations demonstrate the method’s efficacy in handling pose ambiguity, mitigating perspective-induced ambiguity, and showcasing the robustness of our surrogate Stein score formulation on SE(3) . This formulation not only improves the convergence of Langevin dynamics but also enhances computational efficiency. Thus, we pioneer a promising strategy for 6D object pose estimation.
CV-47-标题: A Task-guided Implicitly-searched and Meta-initialized Deep Model for Image Fusion
作者: Risheng Liu, Zhu Liu, Jinyuan Liu, Xin Fan, Zhongxuan Luo
备注: 16 pages, 12 figures, Codes are available at this https URL
Abstract: Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an individual task, thus ignoring its underlying relationship with these downstream vision problems. Furthermore, designing proper fusion architectures often requires huge engineering labor. It also lacks mechanisms to improve the flexibility and generalization ability of current fusion approaches. To mitigate these issues, we establish a Task-guided, Implicit-searched and Meta-initialized (TIM) deep model to address the image fusion problem in a challenging real-world scenario. Specifically, we first propose a constrained strategy to incorporate information from downstream tasks to guide the unsupervised learning process of image fusion. Within this framework, we then design an implicit search scheme to automatically discover compact architectures for our fusion model with high efficiency. In addition, a pretext meta initialization technique is introduced to leverage divergence fusion data to support fast adaptation for different kinds of image fusion tasks. Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e.g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM. The source code will be available at this https URL.
CV-48-标题: Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language SIGIR2023
作者: Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi, Tomáš Rebok
备注: Accepted at SIGIR 2023 (short)
Abstract: Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large volumes of such spatio-temporal skeleton data still remains a challenging problem. In this paper, we propose a novel content-based text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural-language textual description. To define baselines for this uncharted task, we employ the BERT and CLIP language representations to encode the text modality and successful spatio-temporal models to encode the motion modality. We additionally introduce our transformer-based approach, called Motion Transformer (MoT), which employs divided space-time attention to effectively aggregate the different skeleton joints in space and time. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions. Finally, we set up a common evaluation protocol by defining qualitative metrics for assessing the quality of the retrieved motions, targeting the two recently-introduced KIT Motion-Language and HumanML3D datasets. The code for reproducing our results is available at this https URL.
CV-49-标题: Improved Multi-Scale Grid Rendering of Point Clouds for Radar Object Detection Networks
作者: Daniel Köhler, Maurice Quach, Michael Ulrich, Frank Meinl, Bastian Bischoff, Holger Blume
备注: Accepted for presentation at the 2023 26th International Conference on Information Fusion (FUSION2023), June 27-30, 2023, in Charleston (SC), United States of America
Abstract: Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense grid structure is often associated with a loss of information, due to the discretization and aggregation of points. In this paper, we propose a novel architecture, multi-scale KPPillarsBEV, that aims to mitigate the negative effects of grid rendering. Specifically, we propose a novel grid rendering method, KPBEV, which leverages the descriptive power of kernel point convolutions to improve the encoding of local point cloud contexts during grid rendering. In addition, we propose a general multi-scale grid rendering formulation to incorporate multi-scale feature maps into convolutional backbones of detection networks with arbitrary grid rendering methods. We perform extensive experiments on the nuScenes dataset and evaluate the methods in terms of detection performance and computational complexity. The proposed multi-scale KPPillarsBEV architecture outperforms the baseline by 5.37% and the previous state of the art by 2.88% in Car AP4.0 (average precision for a matching threshold of 4 meters) on the nuScenes validation set. Moreover, the proposed single-scale KPBEV grid rendering improves the Car AP4.0 by 2.90% over the baseline while maintaining the same inference speed.
CV-50-标题: All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation
作者: Liyao Tang, Zhe Chen, Shanshan Zhao, Chaoyue Wang, Dacheng Tao
Abstract: Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. Existing methods often rely on empirical label selection strategies, such as confidence thresholding, to generate beneficial pseudo-labels for model training. This approach may, however, hinder the comprehensive exploitation of unlabeled data points. We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly. To address this issue, we propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions. More specifically, our method introduces an Entropy Regularization loss and a Distribution Alignment loss for weakly supervised learning in 3D segmentation tasks, resulting in an ERDA learning strategy. Interestingly, by using KL distance to formulate the distribution alignment loss, it reduces to a deceptively simple cross-entropy-based loss which optimizes both the pseudo-label generation network and the 3D segmentation network simultaneously. Despite the simplicity, our method promisingly improves the performance. We validate the effectiveness through extensive experiments on various baselines and large-scale datasets. Results show that ERDA effectively enables the effective usage of all unlabeled data points for learning and achieves state-of-the-art performance under different settings. Remarkably, our method can outperform fully-supervised baselines using only 1% of true annotations. Code and model will be made publicly available.
CV-51-标题: Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback
作者: Yiqi Lin, Hao Wu, Ruichen Wang, Haonan Lu, Xiaodong Lin, Hui Xiong, Lin Wang
备注: Preprint. Work in Progres
Abstract: Generating and editing a 3D scene guided by natural language poses a challenge, primarily due to the complexity of specifying the positional relations and volumetric changes within the 3D space. Recent advancements in Large Language Models (LLMs) have demonstrated impressive reasoning, conversational, and zero-shot generation abilities across various domains. Surprisingly, these models also show great potential in realizing and interpreting the 3D space. In light of this, we propose a novel language-guided interactive 3D generation system, dubbed LI3D, that integrates LLMs as a 3D layout interpreter into the off-the-shelf layout-to-3D generative models, allowing users to flexibly and interactively generate visual content. Specifically, we design a versatile layout structure base on the bounding boxes and semantics to prompt the LLMs to model the spatial generation and reasoning from language. Our system also incorporates LLaVA, a large language and vision assistant, to provide generative feedback from the visual aspect for improving the visual quality of generated content. We validate the effectiveness of LI3D, primarily in 3D generation and editing through multi-round interactions, which can be flexibly extended to 2D generation and editing. Various experiments demonstrate the potential benefits of incorporating LLMs in generative AI for applications, e.g., metaverse. Moreover, we benchmark the layout reasoning performance of LLMs with neural visual artist tasks, revealing their emergent ability in the spatial layout domain.
CV-52-标题: VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale
作者: Zhiwei Hao, Jianyuan Guo, Kai Han, Han Hu, Chang Xu, Yunhe Wang
Abstract: The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we identify the \emphsmall data pitfall that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K. Specifically, we show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1%, 84.3%, and 85.0% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at this https URL.
CV-53-标题: Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models CVPR2023
作者: Jooyoung Choi, Yunjey Choi, Yunji Kim, Junho Kim, Sungroh Yoon
备注: CVPR 2023 AI4CC Workshop
Abstract: Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to support text-guided image editing. While text guidance is an intuitive editing interface for users, it often fails to ensure the precise concept conveyed by users. To address this issue, we propose Custom-Edit, in which we (i) customize a diffusion model with a few reference images and then (ii) perform text-guided editing. Our key discovery is that customizing only language-relevant parameters with augmented prompts improves reference similarity significantly while maintaining source similarity. Moreover, we provide our recipe for each customization and editing process. We compare popular customization methods and validate our findings on two editing methods using various datasets.
CV-54-标题: Concept-Centric Transformer s: Concept Transformer s with Object-Centric Concept Learning for Interpretability
作者: Jinyung Hong, Theodore P. Pavlic
备注: 20 pages, 7 tables, 15 figures
Abstract: Attention mechanisms have greatly improved the performance of deep-learning models on visual, NLP, and multimodal tasks while also providing tools to aid in the model’s interpretability. In particular, attention scores over input regions or concrete image features can be used to measure how much the attended elements contribute to the model inference. The recently proposed Concept Transformer (CT) generalizes the Transformer attention mechanism from such low-level input features to more abstract, intermediate-level latent concepts that better allow human analysts to more directly assess an explanation for the reasoning of the model about any particular output classification. However, the concept learning employed by CT implicitly assumes that across every image in a class, each image patch makes the same contribution to concepts that characterize membership in that class. Instead of using the CT’s image-patch-centric concepts, object-centric concepts could lead to better classification performance as well as better explainability. Thus, we propose Concept-Centric Transformers (CCT), a new family of concept transformers that provides more robust explanations and performance by integrating a novel concept-extraction module based on object-centric learning. We test our proposed CCT against the CT and several other existing approaches on classification problems for MNIST (odd/even), CIFAR100 (super-classes), and CUB-200-2011 (bird species). Our experiments demonstrate that CCT not only achieves significantly better classification accuracy than all selected benchmark classifiers across all three of our test problems, but it generates more consistent concept-based explanations of classification output when compared to CT.
CV-55-标题: Multi-scale Efficient Graph- Transformer for Whole Slide Image Classification
作者: Saisai Ding, Juncheng Li, Jun Wang, Shihui Ying, Jun Shi
Abstract: The multi-scale information among the whole slide images (WSIs) is essential for cancer diagnosis. Although the existing multi-scale vision Transformer has shown its effectiveness for learning multi-scale image representation, it still cannot work well on the gigapixel WSIs due to their extremely large image sizes. To this end, we propose a novel Multi-scale Efficient Graph-Transformer (MEGT) framework for WSI classification. The key idea of MEGT is to adopt two independent Efficient Graph-based Transformer (EGT) branches to process the low-resolution and high-resolution patch embeddings (i.e., tokens in a Transformer) of WSIs, respectively, and then fuse these tokens via a multi-scale feature fusion module (MFFM). Specifically, we design an EGT to efficiently learn the local-global information of patch tokens, which integrates the graph representation into Transformer to capture spatial-related information of WSIs. Meanwhile, we propose a novel MFFM to alleviate the semantic gap among different resolution patches during feature fusion, which creates a non-patch token for each branch as an agent to exchange information with another branch by cross-attention. In addition, to expedite network training, a novel token pruning module is developed in EGT to reduce the redundant tokens. Extensive experiments on TCGA-RCC and CAMELYON16 datasets demonstrate the effectiveness of the proposed MEGT.
CV-56-标题: High-Similarity-Pass Attention for Single Image Super-Resolution
作者: Jian-Nan Su, Min Gan, Guang-Yong Chen, Wenzhong Guo, C. L. Philip Chen
备注: 13 pages, 12 figures. arXiv admin note: text overlap with arXiv:2212.01057
Abstract: Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR). Researchers usually used the NLA to explore non-local self-similarity (NSS) in SISR and achieve satisfactory reconstruction results. However, a surprising phenomenon that the reconstruction performance of the standard NLA is similar to the NLA with randomly selected regions stimulated our interest to revisit NLA. In this paper, we first analyzed the attention map of the standard NLA from different perspectives and discovered that the resulting probability distribution always has full support for every local feature, which implies a statistical waste of assigning values to irrelevant non-local features, especially for SISR which needs to model long-range dependence with a large number of redundant non-local features. Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution. Furthermore, we derived some key properties of the soft thresholding operation that enable training our HSPA in an end-to-end manner. The HSPA can be integrated into existing deep SISR models as an efficient general building block. In addition, to demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN) by integrating a few HSPAs in a simple backbone. Extensive experimental results demonstrate that HSPAN outperforms state-of-the-art approaches on both quantitative and qualitative evaluations.
CV-57-标题: Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving
作者: Wenhao Cheng, Junbo Yin, Wei Li, Ruigang Yang, Jianbing Shen
Abstract: This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus on the 2D or 3D-indoor domain, which is not suitable for accurately predicting the location of the queried 3D region in an autonomous driving scene. In addition, the upper-bound limitation and the heavy computation cost motivate us to explore a better solution. In this work, we propose a new multi-modal visual grounding task, termed LiDAR Grounding. Then we devise a Multi-modal Single Shot Grounding (MSSG) approach with an effective token fusion strategy. It jointly learns the LiDAR-based object detector with the language features and predicts the targeted region directly from the detector without any post-processing. Moreover, the image feature can be flexibly integrated into our approach to provide rich texture and color information. The cross-modal learning enforces the detector to concentrate on important regions in the point cloud by considering the informative language expressions, thus leading to much better accuracy and efficiency. Extensive experiments on the Talk2Car dataset demonstrate the effectiveness of the proposed methods. Our work offers a deeper insight into the LiDAR-based grounding task and we expect it presents a promising direction for the autonomous driving community.
CV-58-标题: Multi-query Vehicle Re-identification: Viewpoint-conditioned Network Unified Dataset and New Metric
作者: Aihua Zheng, Chaobin Zhang, Weijun Zhang, Chenglong Li, Jin Tang, Chang Tan, Ruoran Jia
Abstract: Existing vehicle re-identification methods mainly rely on the single query, which has limited information for vehicle representation and thus significantly hinders the performance of vehicle Re-ID in complicated surveillance networks. In this paper, we propose a more realistic and easily accessible task, called multi-query vehicle Re-ID, which leverages multiple queries to overcome viewpoint limitation of single one. Based on this task, we make three major contributions. First, we design a novel viewpoint-conditioned network (VCNet), which adaptively combines the complementary information from different vehicle viewpoints, for multi-query vehicle Re-ID. Moreover, to deal with the problem of missing vehicle viewpoints, we propose a cross-view feature recovery module which recovers the features of the missing viewpoints by learnt the correlation between the features of available and missing viewpoints. Second, we create a unified benchmark dataset, taken by 6142 cameras from a real-life transportation surveillance system, with comprehensive viewpoints and large number of crossed scenes of each vehicle for multi-query vehicle Re-ID evaluation. Finally, we design a new evaluation metric, called mean cross-scene precision (mCSP), which measures the ability of cross-scene recognition by suppressing the positive samples with similar viewpoints from same camera. Comprehensive experiments validate the superiority of the proposed method against other methods, as well as the effectiveness of the designed metric in the evaluation of multi-query vehicle Re-ID.
CV-59-标题: Dynamic Enhancement Network for Partial Multi-modality Person Re-identification
作者: Aihua Zheng, Ziling He, Zi Wang, Chenglong Li, Jin Tang
Abstract: Many existing multi-modality studies are based on the assumption of modality integrity. However, the problem of missing arbitrary modalities is very common in real life, and this problem is less studied, but actually important in the task of multi-modality person re-identification (Re-ID). To this end, we design a novel dynamic enhancement network (DENet), which allows missing arbitrary modalities while maintaining the representation ability of multiple modalities, for partial multi-modality person Re-ID. To be specific, the multi-modal representation of the RGB, near-infrared (NIR) and thermal-infrared (TIR) images is learned by three branches, in which the information of missing modalities is recovered by the feature transformation module. Since the missing state might be changeable, we design a dynamic enhancement module, which dynamically enhances modality features according to the missing state in an adaptive manner, to improve the multi-modality representation. Extensive experiments on multi-modality person Re-ID dataset RGBNT201 and vehicle Re-ID dataset RGBNT100 comparing to the state-of-the-art methods verify the effectiveness of our method in complex and changeable environments.
CV-60-标题: T2TD: Text-3D Generation Model based on Prior Knowledge Guidance
作者: Weizhi Nie, Ruidong Chen, Weijie Wang, Bruno Lepri, Nicu Sebe
Abstract: In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models efficiently from textual descriptions is a promising but challenging way to solve this problem. In this paper, inspired by the ability of human beings to complement visual information details from ambiguous descriptions based on their own experience, we propose a novel text-3D generation model (T2TD), which introduces the related shapes or textual information as the prior knowledge to improve the performance of the 3D generation model. In this process, we first introduce the text-3D knowledge graph to save the relationship between 3D models and textual semantic information, which can provide the related shapes to guide the target 3D model generation. Second, we integrate an effective causal inference model to select useful feature information from these related shapes, which removes the unrelated shape information and only maintains feature information that is strongly relevant to the textual description. Meanwhile, to effectively integrate multi-modal prior knowledge into textual information, we adopt a novel multi-layer transformer structure to progressively fuse related shape and textual information, which can effectively compensate for the lack of structural information in the text and enhance the final performance of the 3D generation model. The final experimental results demonstrate that our approach significantly improves 3D model generation quality and outperforms the SOTA methods on the text2shape datasets.
CV-61-标题: ReactFace: Multiple Appropriate Facial Reaction Generation in Dyadic Interactions
作者: Cheng Luo, Siyang Song, Weicheng Xie, Micol Spitale, Linlin Shen, Hatice Gunes
备注: 10 pages, 6 figures
Abstract: In dyadic interaction, predicting the listener’s facial reactions is challenging as different reactions may be appropriate in response to the same speaker’s behaviour. This paper presents a novel framework called ReactFace that learns an appropriate facial reaction distribution from a speaker’s behaviour rather than replicating the real facial reaction of the listener. ReactFace generates multiple different but appropriate photo-realistic human facial reactions by (i) learning an appropriate facial reaction distribution representing multiple appropriate facial reactions; and (ii) synchronizing the generated facial reactions with the speaker’s verbal and non-verbal behaviours at each time stamp, resulting in realistic 2D facial reaction sequences. Experimental results demonstrate the effectiveness of our approach in generating multiple diverse, synchronized, and appropriate facial reactions from each speaker’s behaviour, with the quality of the generated reactions being influenced by the speaker’s speech and facial behaviours. Our code is made publicly available at \urlthis https URL.
CV-62-标题: MPE4G: Multimodal Pretrain ed Encoder for Co-Speech Gesture Generation
作者: Gwantae Kim, Seonghyeok Noh, Insung Ham, Hanseok Ko
备注: 5 pages, 3 figures
Abstract: When virtual agents interact with humans, gestures are crucial to delivering their intentions with speech. Previous multimodal co-speech gesture generation models required encoded features of all modalities to generate gestures. If some input modalities are removed or contain noise, the model may not generate the gestures properly. To acquire robust and generalized encodings, we propose a novel framework with a multimodal pre-trained encoder for co-speech gesture generation. In the proposed method, the multi-head-attention-based encoder is trained with self-supervised learning to contain the information on each modality. Moreover, we collect full-body gestures that consist of 3D joint rotations to improve visualization and apply gestures to the extensible body model. Through the series of experiments and human evaluation, the proposed method renders realistic co-speech gestures not only when all input modalities are given but also when the input modalities are missing or noisy.
CV-63-标题: On the Impact of Knowledge Distillation for Model Interpretability ICML
作者: Hyeongrok Han, Siwon Kim, Hyun-Soo Choi, Sungroh Yoon
备注: International Conference on Machine Learning (ICML) 2023
Abstract: Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields.
CV-64-标题: CLIP3Dstyler: Language Guided 3D Arbitrary Neural Style Transfer
作者: Ming Gao, YanWu Xu, Yang Zhao, Tingbo Hou, Tingbo Hou, Chenkai Zhao, Mingming Gong
备注: 17 pages, 14 figures
Abstract: In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler). We aim at stylizing any 3D scene with an arbitrary style from a text description, and synthesizing the novel stylized view, which is more flexible than the image-conditioned style transfer. Compared with the previous 2D method CLIPStyler, we are able to stylize a 3D scene and generalize to novel scenes without re-train our model. A straightforward solution is to combine previous image-conditioned 3D style transfer and text-conditioned 2D style transfer \bigskip methods. However, such a solution cannot achieve our goal due to two main challenges. First, there is no multi-modal model matching point clouds and language at different feature scales (\eg low-level, high-level). Second, we observe a style mixing issue when we stylize the content with different style conditions from text prompts. To address the first issue, we propose a 3D stylization framework to match the point cloud features with text features in local and global views. For the second issue, we propose an improved directional divergence loss to make arbitrary text styles more distinguishable as a complement to our framework. We conduct extensive experiments to show the effectiveness of our model on text-guided 3D scene style transfer.
CV-65-标题: POPE: 6-DoF Prompt able Pose Estimation of Any Object in Any Scene with One Reference
作者: Zhiwen Fan, Panwang Pan, Peihao Wang, Yifan Jiang, Dejia Xu, Hanwen Jiang, Zhangyang Wang
Abstract: Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation, existing methods have limited applicability in real-world scenarios involving embodied agents and downstream 3D vision tasks. These limitations mainly come from the necessity of 3D models, closed-category detection, and a large number of densely annotated support views. To mitigate this issue, we propose a general paradigm for object pose estimation, called Promptable Object Pose Estimation (POPE). The proposed approach POPE enables zero-shot 6DoF object pose estimation for any target object in any scene, while only a single reference is adopted as the support view. To achieve this, POPE leverages the power of the pre-trained large-scale 2D foundation model, employs a framework with hierarchical feature representation and 3D geometry principles. Moreover, it estimates the relative camera pose between object prompts and the target object in new views, enabling both two-view and multi-view 6DoF pose estimation tasks. Comprehensive experimental results demonstrate that POPE exhibits unrivaled robust performance in zero-shot settings, by achieving a significant reduction in the averaged Median Pose Error by 52.38% and 50.47% on the LINEMOD and OnePose datasets, respectively. We also conduct more challenging testings in causally captured images (see Figure 1), which further demonstrates the robustness of POPE. Project page can be found with this https URL.
CV-66-标题: Knowledge Diffusion for Distillation
作者: Tao Huang, Yuan Zhang, Mingkai Zheng, Shan You, Fei Wang, Chen Qian, Chang Xu
Abstract: The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models. Our approach is based on the observation that student features typically contain more noises than teacher features due to the smaller capacity of student model. To address this, we propose to denoise student features using a diffusion model trained by teacher features. This allows us to perform better distillation between the refined clean feature and teacher feature. Additionally, we introduce a light-weight diffusion model with a linear autoencoder to reduce the computation cost and an adpative noise matching module to improve the denoising performance. Extensive experiments demonstrate that DiffKD is effective across various types of features and achieves state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code will be available at this https URL.
CV-67-标题: CUEING: A pioneer work of encoding human gaze for autonomous driving
作者: Linfeng Liang, Yiran Wang, Yao Deng, Jianchao Lu, Chen Wang, Xi Zheng
Abstract: Recent analysis of incidents involving Autonomous Driving Systems (ADS) has shown that the decision-making process of ADS can be significantly different from that of human drivers. To improve the performance of ADS, it may be helpful to incorporate the human decision-making process, particularly the signals provided by the human gaze. There are many existing works to create human gaze datasets and predict the human gaze using deep learning models. However, current datasets of human gaze are noisy and include irrelevant objects that can hinder model training. Additionally, existing CNN-based models for predicting human gaze lack generalizability across different datasets and driving conditions, and many models have a centre bias in their prediction such that the gaze tends to be generated in the centre of the gaze map. To address these gaps, we propose an adaptive method for cleansing existing human gaze datasets and a robust convolutional self-attention gaze prediction model. Our quantitative metrics show that our cleansing method improves models’ performance by up to 7.38% and generalizability by up to 8.24% compared to those trained on the original datasets. Furthermore, our model demonstrates an improvement of up to 12.13% in terms of generalizability compared to the state-of-the-art (SOTA) models. Notably, it achieves these gains while conserving up to 98.12% of computation resources.
CV-68-标题: PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation
作者: Xianghao Jiao, Yaohua Liu, Jiaxin Gao, Xinyuan Chu, Risheng Liu, Xin Fan
Abstract: In light of the significant progress made in the development and application of semantic segmentation tasks, there has been increasing attention towards improving the robustness of segmentation models against natural degradation factors (e.g., rain streaks) or artificially attack factors (e.g., adversarial attack). Whereas, most existing methods are designed to address a single degradation factor and are tailored to specific application scenarios. In this work, we present the first attempt to improve the robustness of semantic segmentation tasks by simultaneously handling different types of degradation factors. Specifically, we introduce the Preprocessing Enhanced Adversarial Robust Learning (PEARL) framework based on the analysis of our proposed Naive Adversarial Training (NAT) framework. Our approach effectively handles both rain streaks and adversarial perturbation by transferring the robustness of the segmentation model to the image derain model. Furthermore, as opposed to the commonly used Negative Adversarial Attack (NAA), we design the Auxiliary Mirror Attack (AMA) to introduce positive information prior to the training of the PEARL framework, which improves defense capability and segmentation performance. Our extensive experiments and ablation studies based on different derain methods and segmentation models have demonstrated the significant performance improvement of PEARL with AMA in defense against various adversarial attacks and rain streaks while maintaining high generalization performance across different datasets.
CV-69-标题: Score-Based Multimodal Autoencoders
作者: Daniel Wesego, Amirmohammad Rooshenas
Abstract: Multimodal Variational Autoencoders (VAEs) represent a promising group of generative models that facilitate the construction of a tractable posterior within the latent space, given multiple modalities. Daunhawer et al. (2022) demonstrate that as the number of modalities increases, the generative quality of each modality declines. In this study, we explore an alternative approach to enhance the generative performance of multimodal VAEs by jointly modeling the latent space of unimodal VAEs using score-based models (SBMs). The role of the SBM is to enforce multimodal coherence by learning the correlation among the latent variables. Consequently, our model combines the superior generative quality of unimodal VAEs with coherent integration across different modalities.
CV-70-标题: Action Sensitivity Learning for Temporal Action Localization
作者: Jiayi Shao, Xiaohan Wang, Ruijie Quan, Junjun Zheng, Jiang Yang, Yi Yang
备注: 11pages, 4 figures
Abstract: Temporal action localization (TAL), which involves recognizing and locating action instances, is a challenging task in video understanding. Most existing approaches directly predict action classes and regress offsets to boundaries, while overlooking the discrepant importance of each frame. In this paper, we propose an Action Sensitivity Learning framework (ASL) to tackle this task, which aims to assess the value of each frame and then leverage the generated action sensitivity to recalibrate the training procedure. We first introduce a lightweight Action Sensitivity Evaluator to learn the action sensitivity at the class level and instance level, respectively. The outputs of the two branches are combined to reweight the gradient of the two sub-tasks. Moreover, based on the action sensitivity of each frame, we design an Action Sensitive Contrastive Loss to enhance features, where the action-aware frames are sampled as positive pairs to push away the action-irrelevant frames. The extensive studies on various action localization benchmarks (i.e., MultiThumos, Charades, Ego4D-Moment Queries v1.0, Epic-Kitchens 100, Thumos14 and ActivityNet1.3) show that ASL surpasses the state-of-the-art in terms of average-mAP under multiple types of scenarios, e.g., single-labeled, densely-labeled and egocentric.
CV-71-标题: Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
作者: Thanh-Dat Truong, Hoang-Quan Nguyen, Bhiksha Raj, Khoa Luu
Abstract: Continual semantic segmentation aims to learn new classes while maintaining the information from the previous classes. Although prior studies have shown impressive progress in recent years, the fairness concern in the continual semantic segmentation needs to be better addressed. Meanwhile, fairness is one of the most vital factors in deploying the deep learning model, especially in human-related or safety applications. In this paper, we present a novel Fairness Continual Learning approach to the semantic segmentation problem. In particular, under the fairness objective, a new fairness continual learning framework is proposed based on class distributions. Then, a novel Prototypical Contrastive Clustering loss is proposed to address the significant challenges in continual learning, i.e., catastrophic forgetting and background shift. Our proposed loss has also been proven as a novel, generalized learning paradigm of knowledge distillation commonly used in continual learning. Moreover, the proposed Conditional Structural Consistency loss further regularized the structural constraint of the predicted segmentation. Our proposed approach has achieved State-of-the-Art performance on three standard scene understanding benchmarks, i.e., ADE20K, Cityscapes, and Pascal VOC, and promoted the fairness of the segmentation model.
CV-72-标题: Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective
作者: Thanh-Dat Truong, Khoa Luu
Abstract: Understanding action recognition in egocentric videos has emerged as a vital research topic with numerous practical applications. With the limitation in the scale of egocentric data collection, learning robust deep learning-based action recognition models remains difficult. Transferring knowledge learned from the large-scale exocentric data to the egocentric data is challenging due to the difference in videos across views. Our work introduces a novel cross-view learning approach to action recognition (CVAR) that effectively transfers knowledge from the exocentric to the egocentric view. First, we introduce a novel geometric-based constraint into the self-attention mechanism in Transformer based on analyzing the camera positions between two views. Then, we propose a new cross-view self-attention loss learned on unpaired cross-view data to enforce the self-attention mechanism learning to transfer knowledge across views. Finally, to further improve the performance of our cross-view learning approach, we present the metrics to measure the correlations in videos and attention maps effectively. Experimental results on standard egocentric action recognition benchmarks, i.e., Charades-Ego, EPIC-Kitchens-55, and EPIC-Kitchens-100, have shown our approach’s effectiveness and state-of-the-art performance.
CV-73-标题: Learning Occupancy for Monocular 3D Object Detection
作者: Liang Peng, Junkai Xu, Haoran Cheng, Zheng Yang, Xiaopei Wu, Wei Qian, Wenxiao Wang, Boxi Wu, Deng Cai
Abstract: Monocular 3D detection is a challenging task due to the lack of accurate 3D information. Existing approaches typically rely on geometry constraints and dense depth estimates to facilitate the learning, but often fail to fully exploit the benefits of three-dimensional feature extraction in frustum and 3D space. In this paper, we propose \textbfOccupancyM3D, a method of learning occupancy for monocular 3D detection. It directly learns occupancy in frustum and 3D space, leading to more discriminative and informative 3D features and representations. Specifically, by using synchronized raw sparse LiDAR point clouds, we define the space status and generate voxel-based occupancy labels. We formulate occupancy prediction as a simple classification problem and design associated occupancy losses. Resulting occupancy estimates are employed to enhance original frustum/3D features. As a result, experiments on KITTI and Waymo open datasets demonstrate that the proposed method achieves a new state of the art and surpasses other methods by a significant margin. Codes and pre-trained models will be available at \urlthis https URL.
CV-74-标题: Deep Neural Networks in Video Human Action Recognition: A Review
作者: Zihan Wang, Yang Yang, Zhi Liu, Yifan Zheng
Abstract: Currently, video behavior recognition is one of the most foundational tasks of computer vision. The 2D neural networks of deep learning are built for recognizing pixel-level information such as images with RGB, RGB-D, or optical flow formats, with the current increasingly wide usage of surveillance video and more tasks related to human action recognition. There are increasing tasks requiring temporal information for frames dependency analysis. The researchers have widely studied video-based recognition rather than image-based(pixel-based) only to extract more informative elements from geometry tasks. Our current related research addresses multiple novel proposed research works and compares their advantages and disadvantages between the derived deep learning frameworks rather than machine learning frameworks. The comparison happened between existing frameworks and datasets, which are video format data only. Due to the specific properties of human actions and the increasingly wide usage of deep neural networks, we collected all research works within the last three years between 2020 to 2022. In our article, the performance of deep neural networks surpassed most of the techniques in the feature learning and extraction tasks, especially video action recognition.
CV-75-标题: Frame-Event Alignment and Fusion Network for High Frame Rate Tracking
作者: Jiqing Zhang, Yuanchen Wang, Wenxi Liu, Meng Li, Jinpeng Bai, Baocai Yin, Xin Yang
Abstract: Most existing RGB-based trackers target low frame rate benchmarks of around 30 frames per second. This setting restricts the tracker’s functionality in the real world, especially for fast motion. Event-based cameras as bioinspired sensors provide considerable potential for high frame rate tracking due to their high temporal resolution. However, event-based cameras cannot offer fine-grained texture information like conventional cameras. This unique complementarity motivates us to combine conventional frames and events for high frame rate object tracking under various challenging conditions. Inthispaper, we propose an end-to-end network consisting of multi-modality alignment and fusion modules to effectively combine meaningful information from both modalities at different measurement rates. The alignment module is responsible for cross-style and cross-frame-rate alignment between frame and event modalities under the guidance of the moving cues furnished by events. While the fusion module is accountable for emphasizing valuable features and suppressing noise information by the mutual complement between the two modalities. Extensive experiments show that the proposed approach outperforms state-of-the-art trackers by a significant margin in high frame rate tracking. With the FE240hz dataset, our approach achieves high frame rate tracking up to 240Hz.
CV-76-标题: A Similarity Alignment Model for Video Copy Segment Matching
作者: Zhenhua Liu, Feipeng Ma, Tianyi Wang, Fengyun Rao
Abstract: With the development of multimedia technology, Video Copy Detection has been a crucial problem for social media platforms. Meta AI hold Video Similarity Challenge on CVPR 2023 to push the technology forward. In this report, we share our winner solutions on Matching Track. We propose a Similarity Alignment Model(SAM) for video copy segment matching. Our SAM exhibits superior performance compared to other competitors, with a 0.108 / 0.144 absolute improvement over the second-place competitor in Phase 1 / Phase 2. Code is available at this https URL.
CV-77-标题: Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognition
作者: Dongnan Gui, Kai Chen, Haisong Ding, Qiang Huo
Abstract: There are more than 80,000 character categories in Chinese while most of them are rarely used. To build a high performance handwritten Chinese character recognition (HCCR) system supporting the full character set with a traditional approach, many training samples need be collected for each character category, which is both time-consuming and expensive. In this paper, we propose a novel approach to transforming Chinese character glyph images generated from font libraries to handwritten ones with a denoising diffusion probabilistic model (DDPM). Training from handwritten samples of a small character set, the DDPM is capable of mapping printed strokes to handwritten ones, which makes it possible to generate photo-realistic and diverse style handwritten samples of unseen character categories. Combining DDPM-synthesized samples of unseen categories with real samples of other categories, we can build an HCCR system to support the full character set. Experimental results on CASIA-HWDB dataset with 3,755 character categories show that the HCCR systems trained with synthetic samples perform similarly with the one trained with real samples in terms of recognition accuracy. The proposed method has the potential to address HCCR with a larger vocabulary.
CV-78-标题: Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial Vision
作者: Han Gao, Huiyuan Luo, Fei Shen, Zhengtao Zhang
Abstract: Although existing image anomaly detection methods yield impressive results, they are mostly an offline learning paradigm that requires excessive data pre-collection, limiting their adaptability in industrial scenarios with online streaming data. Online learning-based image anomaly detection methods are more compatible with industrial online streaming data but are rarely noticed. For the first time, this paper presents a fully online learning image anomaly detection method, namely LeMO, learning memory for online image anomaly detection. LeMO leverages learnable memory initialized with orthogonal random noise, eliminating the need for excessive data in memory initialization and circumventing the inefficiencies of offline data collection. Moreover, a contrastive learning-based loss function for anomaly detection is designed to enable online joint optimization of memory and image target-oriented features. The presented method is simple and highly effective. Extensive experiments demonstrate the superior performance of LeMO in the online setting. Additionally, in the offline setting, LeMO is also competitive with the current state-of-the-art methods and achieves excellent performance in few-shot scenarios.
CV-79-标题: Meta Adaptive Task Sampling for Few-Domain Generalization
作者: Zheyan Shen, Han Yu, Peng Cui, Jiashuo Liu, Xingxuan Zhang, Linjun Zhou, Furui Liu
Abstract: To ensure the out-of-distribution (OOD) generalization performance, traditional domain generalization (DG) methods resort to training on data from multiple sources with different underlying distributions. And the success of those DG methods largely depends on the fact that there are diverse training distributions. However, it usually needs great efforts to obtain enough heterogeneous data due to the high expenses, privacy issues or the scarcity of data. Thus an interesting yet seldom investigated problem arises: how to improve the OOD generalization performance when the perceived heterogeneity is limited. In this paper, we instantiate a new framework called few-domain generalization (FDG), which aims to learn a generalizable model from very few domains of novel tasks with the knowledge acquired from previous learning experiences on base tasks. Moreover, we propose a Meta Adaptive Task Sampling (MATS) procedure to differentiate base tasks according to their semantic and domain-shift similarity to the novel task. Empirically, we show that the newly introduced FDG framework can substantially improve the OOD generalization performance on the novel task and further combining MATS with episodic training could outperform several state-of-the-art DG baselines on widely used benchmarks like PACS and DomainNet.
CV-80-标题: Characterizing Out-of-Distribution Error via Optimal Transport
作者: Yuzhe Lu, Yilong Qin, Runtian Zhai, Andrew Shen, Ketong Chen, Zhenlin Wang, Soheil Kolouri, Simon Stepputtis, Joseph Campbell, Katia Sycara
Abstract: Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models, so methods of predicting a model’s performance on OOD data without labels are important for machine learning safety. While a number of methods have been proposed by prior work, they often underestimate the actual error, sometimes by a large margin, which greatly impacts their applicability to real tasks. In this work, we identify pseudo-label shift, or the difference between the predicted and true OOD label distributions, as a key indicator to this underestimation. Based on this observation, we introduce a novel method for estimating model performance by leveraging optimal transport theory, Confidence Optimal Transport (COT), and show that it provably provides more robust error estimates in the presence of pseudo-label shift. Additionally, we introduce an empirically-motivated variant of COT, Confidence Optimal Transport with Thresholding (COTT), which applies thresholding to the individual transport costs and further improves the accuracy of COT’s error estimates. We evaluate COT and COTT on a variety of standard benchmarks that induce various types of distribution shift – synthetic, novel subpopulation, and natural – and show that our approaches significantly outperform existing state-of-the-art methods with an up to 3x lower prediction error.
CV-81-标题: Semantic Segmentation by Semantic Proportions
作者: Halil Ibrahim Aysel, Xiaohao Cai, Adam Prügel-Bennett
Abstract: Semantic segmentation is a critical task in computer vision that aims to identify and classify individual pixels in an image, with numerous applications for example autonomous driving and medical image analysis. However, semantic segmentation can be super challenging particularly due to the need for large amounts of annotated data. Annotating images is a time-consuming and costly process, often requiring expert knowledge and significant effort. In this paper, we propose a novel approach for semantic segmentation by eliminating the need of ground-truth segmentation maps. Instead, our approach requires only the rough information of individual semantic class proportions, shortened as semantic proportions. It greatly simplifies the data annotation process and thus will significantly reduce the annotation time and cost, making it more feasible for large-scale applications. Moreover, it opens up new possibilities for semantic segmentation tasks where obtaining the full ground-truth segmentation maps may not be feasible or practical. Extensive experimental results demonstrate that our approach can achieve comparable and sometimes even better performance against the benchmark method that relies on the ground-truth segmentation maps. Utilising semantic proportions suggested in this work offers a promising direction for future research in the field of semantic segmentation.
CV-82-标题: Understanding Label Bias in Single Positive Multi-Label Learning ICLR2023
作者: Julio Arroyo, Pietro Perona, Elijah Cole
备注: ICLR 2023, Tiny Papers Track
Abstract: Annotating data for multi-label classification is prohibitively expensive because every category of interest must be confirmed to be present or absent. Recent work on single positive multi-label (SPML) learning shows that it is possible to train effective multi-label classifiers using only one positive label per image. However, the standard benchmarks for SPML are derived from traditional multi-label classification datasets by retaining one positive label for each training example (chosen uniformly at random) and discarding all other labels. In realistic settings it is not likely that positive labels are chosen uniformly at random. This work introduces protocols for studying label bias in SPML and provides new empirical results.
CV-83-标题: Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
作者: Mingxiao Li, Tingyu Qu, Wei Sun, Marie-Francine Moens
Abstract: Denoising Diffusion Probabilistic Models (DDPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps, which could lead to the problem of exposure bias due to the accumulation of prediction errors over iterations. Previous work has attempted to mitigate this issue by perturbing inputs during training, which consequently mandates the retraining of the DDPM. In this work, we conduct a systematic study of exposure bias in diffusion models and, intriguingly, we find that the exposure bias could be alleviated with a new sampling method, without retraining the model. We empirically and theoretically show that, during inference, for each backward time step t and corresponding state \hatx_t , there might exist another time step t_s which exhibits superior coupling with \hatx_t . Based on this finding, we introduce an inference method named Time-Shift Sampler. Our framework can be seamlessly integrated with existing sampling algorithms, such as DDIM or DDPM, inducing merely minimal additional computations. Experimental results show that our proposed framework can effectively enhance the quality of images generated by existing sampling algorithms.
CV-84-标题: Unsupervised Semantic Correspondence Using Stable Diffusion
作者: Eric Hedlin, Gopal Sharma, Shweta Mahajan, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi
Abstract: Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the semantics of the objects they are asked to generate. In this work we show that, without any training, one can leverage this semantic knowledge within diffusion models to find semantic correspondences – locations in multiple images that have the same semantic meaning. Specifically, given an image, we optimize the prompt embeddings of these models for maximum attention on the regions of interest. These optimized embeddings capture semantic information about the location, which can then be transferred to another image. By doing so we obtain results on par with the strongly supervised state of the art on the PF-Willow dataset and significantly outperform (20.9% relative for the SPair-71k dataset) any existing weakly or unsupervised method on PF-Willow, CUB-200 and SPair-71k datasets.
CV-85-标题: Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation
作者: Jie Bu, Kazi Sajeed Mehrab, Anuj Karpatne
备注: 39 pages
Abstract: Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions. Many previous studies employ autoregressive models to incrementally generate graph components such as nodes and edges. However, as graphs typically lack a natural ordering among their components, converting a graph into a sequence of tokens is not straightforward. While prior works mostly rely on conventional heuristics or graph traversal methods like breadth-first search (BFS) or depth-first search (DFS) to convert graphs to sequences, the impact of ordering on graph generation has largely been unexplored. This paper contributes to this problem by: (1) highlighting the crucial role of ordering in autoregressive graph generation models, (2) proposing a novel theoretical framework that perceives ordering as a dimensionality reduction problem, thereby facilitating a deeper understanding of the relationship between orderings and generated graph accuracy, and (3) introducing “latent sort,” a learning-based ordering scheme to perform dimensionality reduction of graph tokens. Our experimental results showcase the effectiveness of latent sort across a wide range of graph generation tasks, encouraging future works to further explore and develop learning-based ordering schemes for autoregressive graph generation.
CV-86-标题: Differentially Private Synthetic Data via Foundation Model APIs 1: Images
作者: Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Harsha Nori, Sergey Yekhanin
备注: 38 pages, 33 figures
Abstract: Generating differentially private (DP) synthetic data that closely resembles the original private data without leaking sensitive user information is a scalable way to mitigate privacy concerns in the current data-driven world. In contrast to current practices that train customized models for this task, we aim to generate DP Synthetic Data via APIs (DPSDA), where we treat foundation models as blackboxes and only utilize their inference APIs. Such API-based, training-free approaches are easier to deploy as exemplified by the recent surge in the number of API-based apps. These approaches can also leverage the power of large foundation models which are accessible via their inference APIs while the model weights are unreleased. However, this comes with greater challenges due to strictly more restrictive model access and the additional need to protect privacy from the API provider. In this paper, we present a new framework called Private Evolution (PE) to solve this problem and show its initial promise on synthetic images. Surprisingly, PE can match or even outperform state-of-the-art (SOTA) methods without any model training. For example, on CIFAR10 (with ImageNet as the public data), we achieve FID<=7.9 with privacy cost epsilon=0.67, significantly improving the previous SOTA from epsilon=32. We further demonstrate the promise of applying PE on large foundation models such as Stable Diffusion to tackle challenging private datasets with a small number of high-resolution images.
CV-87-标题: Malicious or Benign? Towards Effective Content Moderation for Childrens Videos
作者: Syed Hammad Ahmed, Muhammad Junaid Khan, H. M. Umer Qaisar, Gita Sukthankar
备注: 10 pages, 7 figures, The 36th International FLAIRS Conference
Abstract: Online video platforms receive hundreds of hours of uploads every minute, making manual content moderation impossible. Unfortunately, the most vulnerable consumers of malicious video content are children from ages 1-5 whose attention is easily captured by bursts of color and sound. Scammers attempting to monetize their content may craft malicious children’s videos that are superficially similar to educational videos, but include scary and disgusting characters, violent motions, loud music, and disturbing noises. Prominent video hosting platforms like YouTube have taken measures to mitigate malicious content on their platform, but these videos often go undetected by current content moderation tools that are focused on removing pornographic or copyrighted content. This paper introduces our toolkit Malicious or Benign for promoting research on automated content moderation of children’s videos. We present 1) a customizable annotation tool for videos, 2) a new dataset with difficult to detect test cases of malicious content and 3) a benchmark suite of state-of-the-art video classification models.
CV-88-标题: Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics ICLR2023
作者: Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin
备注: ICLR 2023 TinyPapers
Abstract: Modern neural-network-based no-reference image- and video-quality metrics exhibit performance as high as full-reference metrics. These metrics are widely used to improve visual quality in computer vision methods and compare video processing methods. However, these metrics are not stable to traditional adversarial attacks, which can cause incorrect results. Our goal is to investigate the boundaries of no-reference metrics applicability, and in this paper, we propose a fast adversarial perturbation attack on no-reference quality metrics. The proposed attack (FACPA) can be exploited as a preprocessing step in real-time video processing and compression algorithms. This research can yield insights to further aid in designing of stable neural-network-based no-reference quality metrics.
CV-89-标题: Task-aware Distributed Source Coding under Dynamic Bandwidth
作者: Po-han Li, Sravan Kumar Ankireddy, Ruihan Zhao, Hossein Nourkhiz Mahjoub, Ehsan Moradi-Pari, Ufuk Topcu, Sandeep Chinchali, Hyeji Kim
Abstract: Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data and transmits them to a central node due to limited communication bandwidth. A decoder at the central node decompresses and passes the data to a pre-trained machine learning-based task to generate the final output. Thus, it is important to compress the features that are relevant to the task. Additionally, the final performance depends heavily on the total available bandwidth. In practice, it is common to encounter varying availability in bandwidth, and higher bandwidth results in better performance of the task. We design a novel distributed compression framework composed of independent encoders and a joint decoder, which we call neural distributed principal component analysis (NDPCA). NDPCA flexibly compresses data from multiple sources to any available bandwidth with a single model, reducing computing and storage overhead. NDPCA achieves this by learning low-rank task representations and efficiently distributing bandwidth among sensors, thus providing a graceful trade-off between performance and bandwidth. Experiments show that NDPCA improves the success rate of multi-view robotic arm manipulation by 9% and the accuracy of object detection tasks on satellite imagery by 14% compared to an autoencoder with uniform bandwidth allocation.
CV-90-标题: Weakly Supervised Vision-and-Language Pre-training with Relative Representations ACL2023
作者: Chi Chen, Peng Li, Maosong Sun, Yang Liu
备注: Accepted by ACL 2023
Abstract: Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaining decent performance on downstream tasks. However, current WVLP methods use only local descriptions of images, i.e., object tags, as cross-modal anchors to construct weakly-aligned image-text pairs for pre-training. This affects the data quality and thus the effectiveness of pre-training. In this paper, we propose to directly take a small number of aligned image-text pairs as anchors, and represent each unaligned image and text by its similarities to these anchors, i.e., relative representations. We build a WVLP framework based on the relative representations, namely RELIT, which collects high-quality weakly-aligned image-text pairs from large-scale image-only and text-only data for pre-training through relative representation-based retrieval and generation. Experiments on four downstream tasks show that RELIT achieves new state-of-the-art results under the weakly supervised setting.
CV-91-标题: Transcending Grids: Point Clouds and Surface Representations Powering Neurological Processing
作者: Kishore Babu Nampalle, Pradeep Singh, Vivek Narayan Uppala, Sumit Gangwar, Rajesh Singh Negi, Balasubramanian Raman
Abstract: In healthcare, accurately classifying medical images is vital, but conventional methods often hinge on medical data with a consistent grid structure, which may restrict their overall performance. Recent medical research has been focused on tweaking the architectures to attain better performance without giving due consideration to the representation of data. In this paper, we present a novel approach for transforming grid based data into its higher dimensional representations, leveraging unstructured point cloud data structures. We first generate a sparse point cloud from an image by integrating pixel color information as spatial coordinates. Next, we construct a hypersurface composed of points based on the image dimensions, with each smooth section within this hypersurface symbolizing a specific pixel location. Polygonal face construction is achieved using an adjacency tensor. Finally, a dense point cloud is generated by densely sampling the constructed hypersurface, with a focus on regions of higher detail. The effectiveness of our approach is demonstrated on a publicly accessible brain tumor dataset, achieving significant improvements over existing classification techniques. This methodology allows the extraction of intricate details from the original image, opening up new possibilities for advanced image analysis and processing tasks.
CV-92-标题: Facial Expression Recognition at the Edge: CPU vs GPU vs VPU vs TPU
作者: Mohammadreza Mohammadi, Heath Smith, Lareb Khan, Ramtin Zand
Abstract: Facial Expression Recognition (FER) plays an important role in human-computer interactions and is used in a wide range of applications. Convolutional Neural Networks (CNN) have shown promise in their ability to classify human facial expressions, however, large CNNs are not well-suited to be implemented on resource- and energy-constrained IoT devices. In this work, we present a hierarchical framework for developing and optimizing hardware-aware CNNs tuned for deployment at the edge. We perform a comprehensive analysis across various edge AI accelerators including NVIDIA Jetson Nano, Intel Neural Compute Stick, and Coral TPU. Using the proposed strategy, we achieved a peak accuracy of 99.49% when testing on the CK+ facial expression recognition dataset. Additionally, we achieved a minimum inference latency of 0.39 milliseconds and a minimum power consumption of 0.52 Watts.
CV-93-标题: A Hybrid Semantic-Geometric Approach for Clutter-Resistant Floorplan Generation from Building Point Clouds
作者: Seongyong Kim, Yosuke Yajima, Jisoo Park, Jingdao Chen, Yong K. Cho
Abstract: Building Information Modeling (BIM) technology is a key component of modern construction engineering and project management workflows. As-is BIM models that represent the spatial reality of a project site can offer crucial information to stakeholders for construction progress monitoring, error checking, and building maintenance purposes. Geometric methods for automatically converting raw scan data into BIM models (Scan-to-BIM) often fail to make use of higher-level semantic information in the data. Whereas, semantic segmentation methods only output labels at the point level without creating object level models that is necessary for BIM. To address these issues, this research proposes a hybrid semantic-geometric approach for clutter-resistant floorplan generation from laser-scanned building point clouds. The input point clouds are first pre-processed by normalizing the coordinate system and removing outliers. Then, a semantic segmentation network based on PointNet++ is used to label each point as ceiling, floor, wall, door, stair, and clutter. The clutter points are removed whereas the wall, door, and stair points are used for 2D floorplan generation. A region-growing segmentation algorithm paired with geometric reasoning rules is applied to group the points together into individual building elements. Finally, a 2-fold Random Sample Consensus (RANSAC) algorithm is applied to parameterize the building elements into 2D lines which are used to create the output floorplan. The proposed method is evaluated using the metrics of precision, recall, Intersection-over-Union (IOU), Betti error, and warping error.
CV-94-标题: Trans-Dimensional Generative Modeling via Jump Diffusion Models
作者: Andrew Campbell, William Harvey, Christian Weilbach, Valentin De Bortoli, Tom Rainforth, Arnaud Doucet
备注: 38 pages, 11 figures, 5 tables
Abstract: We propose a new class of generative models that naturally handle data of varying dimensionality by jointly modeling the state and dimension of each datapoint. The generative process is formulated as a jump diffusion process that makes jumps between different dimensional spaces. We first define a dimension destroying forward noising process, before deriving the dimension creating time-reversed generative process along with a novel evidence lower bound training objective for learning to approximate it. Simulating our learned approximation to the time-reversed generative process then provides an effective way of sampling data of varying dimensionality by jointly generating state values and dimensions. We demonstrate our approach on molecular and video datasets of varying dimensionality, reporting better compatibility with test-time diffusion guidance imputation tasks and improved interpolation capabilities versus fixed dimensional models that generate state values and dimensions separately.
CV-95-标题: Incomplete Multimodal Learning for Complex Brain Disorders Prediction
作者: Reza Shirkavand, Liang Zhan, Heng Huang, Li Shen, Paul M. Thompson
Abstract: Recent advancements in the acquisition of various brain data sources have created new opportunities for integrating multimodal brain data to assist in early detection of complex brain disorders. However, current data integration approaches typically need a complete set of biomedical data modalities, which may not always be feasible, as some modalities are only available in large-scale research cohorts and are prohibitive to collect in routine clinical practice. Especially in studies of brain diseases, research cohorts may include both neuroimaging data and genetic data, but for practical clinical diagnosis, we often need to make disease predictions only based on neuroimages. As a result, it is desired to design machine learning models which can use all available data (different data could provide complementary information) during training but conduct inference using only the most common data modality. We propose a new incomplete multimodal data integration approach that employs transformers and generative adversarial networks to effectively exploit auxiliary modalities available during training in order to improve the performance of a unimodal model at inference. We apply our new method to predict cognitive degeneration and disease outcomes using the multimodal imaging genetic data from Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. Experimental results demonstrate that our approach outperforms the related machine learning and deep learning methods by a significant margin.
CV-96-标题: NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation
作者: Pengcheng Shi, Xutao Guo, Yanwu Yang, Chenfei Ye, Ting Ma
备注: 13 pages, 6 figures
Abstract: Convolutional neural networks (CNN) and Transformer variants have emerged as the leading medical image segmentation backbones. Nonetheless, due to their limitations in either preserving global image context or efficiently processing irregular shapes in visual objects, these backbones struggle to effectively integrate information from diverse anatomical regions and reduce inter-individual variability, particularly for the vasculature. Motivated by the successful breakthroughs of graph neural networks (GNN) in capturing topological properties and non-Euclidean relationships across various fields, we propose NexToU, a novel hybrid architecture for medical image segmentation. NexToU comprises improved Pool GNN and Swin GNN modules from Vision GNN (ViG) for learning both global and local topological representations while minimizing computational costs. To address the containment and exclusion relationships among various anatomical structures, we reformulate the topological interaction (TI) module based on the nature of binary trees, rapidly encoding the topological constraints into NexToU. Extensive experiments conducted on three datasets (including distinct imaging dimensions, disease types, and imaging modalities) demonstrate that our method consistently outperforms other state-of-the-art (SOTA) architectures. All the code is publicly available at this https URL.
CV-97-标题: A Diffusion Probabilistic Prior for Low-Dose CT Image Denoising
作者: Xuan Liu, Yaoqin Xie, Songhui Diao, Shan Tan, Xiaokun Liang
Abstract: Low-dose computed tomography (CT) image denoising is crucial in medical image computing. Recent years have been remarkable improvement in deep learning-based methods for this task. However, training deep denoising neural networks requires low-dose and normal-dose CT image pairs, which are difficult to obtain in the clinic settings. To address this challenge, we propose a novel fully unsupervised method for low-dose CT image denoising, which is based on denoising diffusion probabilistic model – a powerful generative model. First, we train an unconditional denoising diffusion probabilistic model capable of generating high-quality normal-dose CT images from random noise. Subsequently, the probabilistic priors of the pre-trained diffusion model are incorporated into a Maximum A Posteriori (MAP) estimation framework for iteratively solving the image denoising problem. Our method ensures the diffusion model produces high-quality normal-dose CT images while keeping the image content consistent with the input low-dose CT images. We evaluate our method on a widely used low-dose CT image denoising benchmark, and it outperforms several supervised low-dose CT image denoising methods in terms of both quantitative and visual performance.
CV-98-标题: Leveraging object detection for the identification of lung cancer
作者: Karthick Prasad Gunasekaran
Abstract: Lung cancer poses a significant global public health challenge, emphasizing the importance of early detection for improved patient outcomes. Recent advancements in deep learning algorithms have shown promising results in medical image analysis. This study aims to explore the application of object detection particularly YOLOv5, an advanced object identification system, in medical imaging for lung cancer identification. To train and evaluate the algorithm, a dataset comprising chest X-rays and corresponding annotations was obtained from Kaggle. The YOLOv5 model was employed to train an algorithm capable of detecting cancerous lung lesions. The training process involved optimizing hyperparameters and utilizing augmentation techniques to enhance the model’s performance. The trained YOLOv5 model exhibited exceptional proficiency in identifying lung cancer lesions, displaying high accuracy and recall rates. It successfully pinpointed malignant areas in chest radiographs, as validated by a separate test set where it outperformed previous techniques. Additionally, the YOLOv5 model demonstrated computational efficiency, enabling real-time detection and making it suitable for integration into clinical procedures. This proposed approach holds promise in assisting radiologists in the early discovery and diagnosis of lung cancer, ultimately leading to prompt treatment and improved patient outcomes.
CV-99-标题: Dynamic Data Augmentation via MCTS for Prostate MRI Segmentation
作者: Xinyue Xu, Yuhan Hsi, Haonan Wang, Xiaomeng Li
Abstract: Medical image data are often limited due to the expensive acquisition and annotation process. Hence, training a deep-learning model with only raw data can easily lead to overfitting. One solution to this problem is to augment the raw data with various transformations, improving the model’s ability to generalize to new data. However, manually configuring a generic augmentation combination and parameters for different datasets is non-trivial due to inconsistent acquisition approaches and data distributions. Therefore, automatic data augmentation is proposed to learn favorable augmentation strategies for different datasets while incurring large GPU overhead. To this end, we present a novel method, called Dynamic Data Augmentation (DDAug), which is efficient and has negligible computation cost. Our DDAug develops a hierarchical tree structure to represent various augmentations and utilizes an efficient Monte-Carlo tree searching algorithm to update, prune, and sample the tree. As a result, the augmentation pipeline can be optimized for each dataset automatically. Experiments on multiple Prostate MRI datasets show that our method outperforms the current state-of-the-art data augmentation strategies.
CV-100-标题: Towards Large-scale Single-shot Millimeter-wave Imaging for Low-cost Security Inspection
作者: Liheng Bian, Daoyu Li, Shuoguang Wang, Huteng Liu, Chunyang Teng, Hanwen Xu, Rike Jie, Xuyang Chang, Guoqiang Zhao, Houjun Sun, Shiyong Li, Jun Zhang
Abstract: Millimeter-wave (MMW) imaging is emerging as a promising technique for safe security inspection. It achieves a delicate balance between imaging resolution, penetrability and human safety, resulting in higher resolution compared to low-frequency microwave, stronger penetrability compared to visible light, and stronger safety compared to X ray. Despite of recent advance in the last decades, the high cost of requisite large-scale antenna array hinders widespread adoption of MMW imaging in practice. To tackle this challenge, we report a large-scale single-shot MMW imaging framework using sparse antenna array, achieving low-cost but high-fidelity security inspection under an interpretable learning scheme. We first collected extensive full-sampled MMW echoes to study the statistical ranking of each element in the large-scale array. These elements are then sampled based on the ranking, building the experimentally optimal sparse sampling strategy that reduces the cost of antenna array by up to one order of magnitude. Additionally, we derived an untrained interpretable learning scheme, which realizes robust and accurate image reconstruction from sparsely sampled echoes. Last, we developed a neural network for automatic object detection, and experimentally demonstrated successful detection of concealed centimeter-sized targets using 10% sparse array, whereas all the other contemporary approaches failed at the same sample sampling ratio. The performance of the reported technique presents higher than 50% superiority over the existing MMW imaging schemes on various metrics including precision, recall, and mAP50. With such strong detection ability and order-of-magnitude cost reduction, we anticipate that this technique provides a practical way for large-scale single-shot MMW imaging, and could advocate its further practical applications.
CV-101-标题: Nonlinear Bipartite Output Regulation with Application to Turing Pattern
作者: Dong Liang, Martin Guay, Shimin Wang
备注: 8 pages,six figures
Abstract: In this paper, a bipartite output regulation problem is solved for a class of nonlinear multi-agent systems subject to static signed communication networks. A nonlinear distributed observer is proposed for a nonlinear exosystem with cooperation-competition interactions to address the problem. Sufficient conditions are provided to guarantee its existence and stability. The exponential stability of the observer is established. As a practical application, a leader-following bipartite consensus problem is solved for a class of nonlinear multi-agent systems based on the observer. Finally, a network of multiple pendulum systems is treated to support the feasibility of the proposed design. The possible application of the approach to generate specific Turing patterns is also presented.
CV-102-标题: High-Throughput AI Inference for Medical Image Classification and Segmentation using Intelligent Streaming
作者: Pranav Kulkarni, Sean Garin, Adway Kanhere, Eliot Siegel, Paul H. Yi, Vishwa S. Parekh
备注: 10 pages, 2 figures, 4 tables, patent pending
Abstract: As the adoption of AI systems within the clinical setup grows, limitations in bandwidth could create communication bottlenecks when streaming imaging data, leading to delays in patient diagnosis and treatment. As such, healthcare providers and AI vendors will require greater computational infrastructure, therefore dramatically increasing costs. To that end, we developed intelligent streaming, a state-of-the-art framework to enable accelerated, cost-effective, bandwidth-optimized, and computationally efficient AI inference for clinical decision making at scale. For classification, intelligent streaming reduced the data transmission by 99.01% and decoding time by 98.58%, while increasing throughput by 27.43x. For segmentation, our framework reduced data transmission by 90.32%, decoding time by 90.26%, while increasing throughput by 4.20x. Our work demonstrates that intelligent streaming results in faster turnaround times, and reduced overall cost of data and transmission, without negatively impacting clinical decision making using AI systems.
CV-103-标题: Generative Adversarial Networks for Brain Images Synthesis: A Review
作者: Firoozeh Shomal Zadeh, Sevda Molani, Maysam Orouskhani, Marziyeh Rezaei, Mehrzad Shafiei, Hossein Abbasi
备注: 9 pages, 3 tabels, 4 figures
Abstract: In medical imaging, image synthesis is the estimation process of one image (sequence, modality) from another image (sequence, modality). Since images with different modalities provide diverse biomarkers and capture various features, multi-modality imaging is crucial in medicine. While multi-screening is expensive, costly, and time-consuming to report by radiologists, image synthesis methods are capable of artificially generating missing modalities. Deep learning models can automatically capture and extract the high dimensional features. Especially, generative adversarial network (GAN) as one of the most popular generative-based deep learning methods, uses convolutional networks as generators, and estimated images are discriminated as true or false based on a discriminator network. This review provides brain image synthesis via GANs. We summarized the recent developments of GANs for cross-modality brain image synthesis including CT to PET, CT to MRI, MRI to PET, and vice versa.
CV-104-标题: Entropy-Aware Similarity for Balanced Clustering: A Case Study with Melanoma Detection
作者: Seok Bin Son, Soohyun Park, Joongheon Kim
Abstract: Clustering data is an unsupervised learning approach that aims to divide a set of data points into multiple groups. It is a crucial yet demanding subject in machine learning and data mining. Its successful applications span various fields. However, conventional clustering techniques necessitate the consideration of balance significance in specific applications. Therefore, this paper addresses the challenge of imbalanced clustering problems and presents a new method for balanced clustering by utilizing entropy-aware similarity, which can be defined as the degree of balances. We have coined the term, entropy-aware similarity for balanced clustering (EASB), which maximizes balance during clustering by complementary clustering of unbalanced data and incorporating entropy in a novel similarity formula that accounts for both angular differences and distances. The effectiveness of the proposed approach is evaluated on actual melanoma medial data, specifically the International Skin Imaging Collaboration (ISIC) 2019 and 2020 challenge datasets, to demonstrate how it can successfully cluster the data while preserving balance. Lastly, we can confirm that the proposed method exhibited outstanding performance in detecting melanoma, comparing to classical methods.
CV-105-标题: Advanced Medical Image Representation for Efficient Processing and Transfer in Multisite Clouds
作者: Elena-Simona Apostol, Ciprian-Octavian Truică
Abstract: An important topic in medical research is the process of improving the images obtained from medical devices. As a consequence, there is also a need to improve medical image resolution and analysis. Another issue in this field is the large amount of stored medical data . Human brain databases at medical institutes, for example, can accumulate tens of Terabytes of data per year. In this paper, we propose a novel medical image format representation based on multiple data structures that improve the information maintained in the medical images. The new representation keeps additional metadata information, such as the image class or tags for the objects found in the image. We defined our own ontology to help us classify the objects found in medical images using a multilayer neural network. As we generally deal with large data sets, we used the MapReduce paradigm in the Cloud environment to speed up the image processing. To optimize the transfer between Cloud nodes and to reduce the preprocessing time, we also propose a data compression method based on deduplication. We test our solution for image representation and efficient data transfer in a multisite cloud environment. Our proposed solution optimizes the data transfer with a time improvement of 27% on average.
IR-0-标题: A Survey on Asking Clarification Questions Dataset s in Conversational Systems ACL2023
作者: Hossein A. Rahmani, Xi Wang, Yue Feng, Qiang Zhang, Emine Yilmaz, Aldo Lipani
备注: ACL 2023, 17 pages
Abstract: The ability to understand a user’s underlying needs is critical for conversational systems, especially with limited input from users in a conversation. Thus, in such a domain, Asking Clarification Questions (ACQs) to reveal users’ true intent from their queries or utterances arise as an essential task. However, it is noticeable that a key limitation of the existing ACQs studies is their incomparability, from inconsistent use of data, distinct experimental setups and evaluation strategies. Therefore, in this paper, to assist the development of ACQs techniques, we comprehensively analyse the current ACQs research status, which offers a detailed comparison of publicly available datasets, and discusses the applied evaluation metrics, joined with benchmarks for multiple ACQs-related tasks. In particular, given a thorough analysis of the ACQs task, we discuss a number of corresponding research directions for the investigation of ACQs as well as the development of conversational systems.
IR-1-标题: Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors
作者: George Zerveas, Navid Rekabsaz, Carsten Eickhoff
Abstract: Sparse annotation poses persistent challenges to training dense retrieval models, such as the problem of false negatives, i.e. unlabeled relevant documents that are spuriously used as negatives in contrastive learning, distorting the training signal. To alleviate this problem, we introduce evidence-based label smoothing, a computationally efficient method that prevents penalizing the model for assigning high relevance to false negatives. To compute the target relevance distribution over candidate documents within the ranking context of a given query, candidates most similar to the ground truth are assigned a non-zero relevance probability based on the degree of their similarity to the ground-truth document(s). As a relevance estimate we leverage an improved similarity metric based on reciprocal nearest neighbors, which can also be used independently to rerank candidates in post-processing. Through extensive experiments on two large-scale ad hoc text retrieval datasets we demonstrate that both methods can improve the ranking effectiveness of dense retrieval models.
AI-0-标题: Fine-Grained Complexity Analysis of Multi-Agent Path Finding on 2D Grids
作者: Tzvika Geft
备注: To appear in Symposium on Combinatorial Search (SoCS 2023)
Abstract: Multi-Agent Path Finding (MAPF) is a fundamental motion coordination problem arising in multi-agent systems with a wide range of applications. The problem’s intractability has led to extensive research on improving the scalability of solvers for it. Since optimal solvers can struggle to scale, a major challenge that arises is understanding what makes MAPF hard. We tackle this challenge through a fine-grained complexity analysis of time-optimal MAPF on 2D grids, thereby closing two gaps and identifying a new tractability frontier. First, we show that 2-colored MAPF, i.e., where the agents are divided into two teams, each with its own set of targets, remains NP-hard. Second, for the flowtime objective (also called sum-of-costs), we show that it remains NP-hard to find a solution in which agents have an individually optimal cost, which we call an individually optimal solution. The previously tightest results for these MAPF variants are for (non-grid) planar graphs. We use a single hardness construction that replaces, strengthens, and unifies previous proofs. We believe that it is also simpler than previous proofs for the planar case as it employs minimal gadgets that enable its full visualization in one figure. Finally, for the flowtime objective, we establish a tractability frontier based on the number of directions agents can move in. Namely, we complement our hardness result, which holds for three directions, with an efficient algorithm for finding an individually optimal solution if only two directions are allowed. This result sheds new light on the structure of optimal solutions, which may help guide algorithm design for the general problem.
AI-1-标题: On Computing Universal Plans for Partially Observable Multi-Agent Path Finding
作者: Fengming Zhu, Fangzhen Lin
Abstract: Multi-agent routing problems have drawn significant attention nowadays due to their broad industrial applications in, e.g., warehouse robots, logistics automation, and traffic control. Conventionally, they are modelled as classical planning problems. In this paper, we argue that it is beneficial to formulate them as universal planning problems. We therefore propose universal plans, also known as policies, as the solution concepts, and implement a system called ASP-MAUPF (Answer Set Programming for Multi-Agent Universal Plan Finding) for computing them. Given an arbitrary two-dimensional map and a profile of goals for the agents, the system finds a feasible universal plan for each agent that ensures no collision with others. We use the system to conduct some experiments, and make some observations on the types of goal profiles and environments that will have feasible policies, and how they may depend on agents’ sensors. We also demonstrate how users can customize action preferences to compute more efficient policies, even (near-)optimal ones.
AI-2-标题: UpMax: User partitioning for MaxSAT
作者: Pedro Orvalho, Vasco Manquinho, Ruben Martins
备注: 17 pages, 6 figures, 2 tables. this https URL
Abstract: It has been shown that Maximum Satisfiability (MaxSAT) problem instances can be effectively solved by partitioning the set of soft clauses into several disjoint sets. The partitioning methods can be based on clause weights (e.g., stratification) or based on graph representations of the formula. Afterwards, a merge procedure is applied to guarantee that an optimal solution is found. This paper proposes a new framework called UpMax that decouples the partitioning procedure from the MaxSAT solving algorithms. As a result, new partitioning procedures can be defined independently of the MaxSAT algorithm to be used. Moreover, this decoupling also allows users that build new MaxSAT formulas to propose partition schemes based on knowledge of the problem to be solved. We illustrate this approach using several problems and show that partitioning has a large impact on the performance of unsatisfiability-based MaxSAT algorithms.
AI-3-标题: Multi-Agent Reinforcement Learning for Network Routing in Integrated Access Backhaul Networks
作者: Shahaf Yamin, Haim Permuter
备注: arXiv admin note: text overlap with arXiv:2110.14541, arXiv:1910.04041, arXiv:1911.10635 by other authors
Abstract: We investigate the problem of wireless routing in integrated access backhaul (IAB) networks consisting of fiber-connected and wireless base stations and multiple users. The physical constraints of these networks prevent the use of a central controller, and base stations have limited access to real-time network conditions. We aim to maximize packet arrival ratio while minimizing their latency, for this purpose, we formulate the problem as a multi-agent partially observed Markov decision process (POMDP). To solve this problem, we develop a Relational Advantage Actor Critic (Relational A2C) algorithm that uses Multi-Agent Reinforcement Learning (MARL) and information about similar destinations to derive a joint routing policy on a distributed basis. We present three training paradigms for this algorithm and demonstrate its ability to achieve near-centralized performance. Our results show that Relational A2C outperforms other reinforcement learning algorithms, leading to increased network efficiency and reduced selfish agent behavior. To the best of our knowledge, this work is the first to optimize routing strategy for IAB networks.
AI-4-标题: PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation AAAI2023
作者: Xinting Liao, Weiming Liu, Xiaolin Zheng, Binhui Yao, Chaochao Chen
备注: To be appear in AAAI2023
Abstract: Privacy-preserving cross-domain recommendation (PPCDR) refers to preserving the privacy of users when transferring the knowledge from source domain to target domain for better performance, which is vital for the long-term development of recommender systems. Existing work on cross-domain recommendation (CDR) reaches advanced and satisfying recommendation performance, but mostly neglects preserving privacy. To fill this gap, we propose a privacy-preserving generative cross-domain recommendation (PPGenCDR) framework for PPCDR. PPGenCDR includes two main modules, i.e., stable privacy-preserving generator module, and robust cross-domain recommendation module. Specifically, the former isolates data from different domains with a generative adversarial network (GAN) based model, which stably estimates the distribution of private data in the source domain with Renyi differential privacy (RDP) technique. Then the latter aims to robustly leverage the perturbed but effective knowledge from the source domain with the raw data in target domain to improve recommendation performance. Three key modules, i.e., (1) selective privacy preserver, (2) GAN stabilizer, and (3) robustness conductor, guarantee the cost-effective trade-off between utility and privacy, the stability of GAN when using RDP, and the robustness of leveraging transferable knowledge accordingly. The extensive empirical studies on Douban and Amazon datasets demonstrate that PPGenCDR significantly outperforms the state-of-the-art recommendation models while preserving privacy.
AI-5-标题: A New Era of Mobility: Exploring Digital Twin Applications in Autonomous Vehicular Systems
作者: S M Mostaq Hossain, Sohag Kumar Saha, Shampa Banik, Trapa Banik
备注: 7 pages, conference paper, accepted for publication in IEEE AIIoT 2023 conference
Abstract: Digital Twins (DTs) are virtual representations of physical objects or processes that can collect information from the real environment to represent, validate, and replicate the physical twin’s present and future behavior. The DTs are becoming increasingly prevalent in a variety of fields, including manufacturing, automobiles, medicine, smart cities, and other related areas. In this paper, we presented a systematic reviews on DTs in the autonomous vehicular industry. We addressed DTs and their essential characteristics, emphasized on accurate data collection, real-time analytics, and efficient simulation capabilities, while highlighting their role in enhancing performance and reliability. Next, we explored the technical challenges and central technologies of DTs. We illustrated the comparison analysis of different methodologies that have been used for autonomous vehicles in smart cities. Finally, we addressed the application challenges and limitations of DTs in the autonomous vehicular industry.
AI-6-标题: Understanding the Capabilities of Large Language Models for Automated Planning
作者: Vishal Pallagani, Bharath Muppasani, Keerthiram Murugesan, Francesca Rossi, Biplav Srivastava, Lior Horesh, Francesco Fabiano, Andrea Loreggia
备注: 12 pages
Abstract: Automated planning is concerned with developing efficient algorithms to generate plans or sequences of actions to achieve a specific goal in a given environment. Emerging Large Language Models (LLMs) can answer questions, write high-quality programming code, and predict protein folding, showcasing their versatility in solving various tasks beyond language-based problems. In this paper, we aim to explore how LLMs can also be used for automated planning. To do so, we seek to answer four key questions. Firstly, we want to understand the extent to which LLMs can be used for plan generation. Secondly, we aim to identify which pre-training data is most effective in facilitating plan generation. Thirdly, we investigate whether fine-tuning or prompting is a more effective approach for plan generation. Finally, we explore whether LLMs are capable of plan generalization. By answering these questions, the study seeks to shed light on the capabilities of LLMs in solving complex planning problems and provide insights into the most effective approaches for using LLMs in this context.
AI-7-标题: AI Techniques in the Microservices Life-Cycle: A Survey
作者: Sergio Moreschini, Shahrzad Pour, Ivan Lanese, Daniel Balouek-Thomert, Justus Bogner, Xiaozhou Li, Fabiano Pecorelli, Jacopo Soldani, Eddy Truyen, Davide Taibi
备注: Currently under review at the Journal of Systems and Software (JSS)
Abstract: Microservices is a popular architectural style for the development of distributed software, with an emphasis on modularity, scalability, and flexibility. Indeed, in microservice systems, functionalities are provided by loosely coupled, small services, each focusing on a specific business capability. Building a system according to the microservices architectural style brings a number of challenges, mainly related to how the different microservices are deployed and coordinated and how they interact. In this paper, we provide a survey about how techniques in the area of Artificial Intelligence have been used to tackle these challenges.
AI-8-标题: Monitoring Algorithmic Fairness
作者: Thomas A. Henzinger, Mahyar Karimi, Konstantin Kueffner, Kaushik Mallik
备注: CAV 2023
Abstract: Machine-learned systems are in widespread use for making decisions about humans, and it is important that they are fair, i.e., not biased against individuals based on sensitive attributes. We present runtime verification of algorithmic fairness for systems whose models are unknown, but are assumed to have a Markov chain structure. We introduce a specification language that can model many common algorithmic fairness properties, such as demographic parity, equal opportunity, and social burden. We build monitors that observe a long sequence of events as generated by a given system, and output, after each observation, a quantitative estimate of how fair or biased the system was on that run until that point in time. The estimate is proven to be correct modulo a variable error bound and a given confidence level, where the error bound gets tighter as the observed sequence gets longer. Our monitors are of two types, and use, respectively, frequentist and Bayesian statistical inference techniques. While the frequentist monitors compute estimates that are objectively correct with respect to the ground truth, the Bayesian monitors compute estimates that are correct subject to a given prior belief about the system’s model. Using a prototype implementation, we show how we can monitor if a bank is fair in giving loans to applicants from different social backgrounds, and if a college is fair in admitting students while maintaining a reasonable financial burden on the society. Although they exhibit different theoretical complexities in certain cases, in our experiments, both frequentist and Bayesian monitors took less than a millisecond to update their verdicts after each observation.
AI-9-标题: Improved Algorithms for Allens Interval Algebra by Dynamic Programming with Sublinear Partitioning
作者: Leif Eriksson, Victor Lagerkvist
Abstract: Allen’s interval algebra is one of the most well-known calculi in qualitative temporal reasoning with numerous applications in artificial intelligence. Recently, there has been a surge of improvements in the fine-grained complexity of NP-hard reasoning tasks, improving the running time from the naive 2^O(n^2) to O^((1.0615n)^n) , with even faster algorithms for unit intervals a bounded number of overlapping intervals (the O^(\cdot) notation suppresses polynomial factors). Despite these improvements the best known lower bound is still only 2^o(n) (under the exponential-time hypothesis) and major improvements in either direction seemingly require fundamental advances in computational complexity. In this paper we propose a novel framework for solving NP-hard qualitative reasoning problems which we refer to as dynamic programming with sublinear partitioning. Using this technique we obtain a major improvement of O^((\fraccn\logn)^n) for Allen’s interval algebra. To demonstrate that the technique is applicable to more domains we apply it to a problem in qualitative spatial reasoning, the cardinal direction point algebra, and solve it in O^((\fraccn\logn)^2n/3) time. Hence, not only do we significantly advance the state-of-the-art for NP-hard qualitative reasoning problems, but obtain a novel algorithmic technique that is likely applicable to many problems where 2^O(n) time algorithms are unlikely.
AI-10-标题: Learning to Act through Evolution of Neural Diversity in Random Neural Networks
作者: Joachim Winther Pedersen, Sebastian Risi
Abstract: Biological nervous systems consist of networks of diverse, sophisticated information processors in the form of neurons of different classes. In most artificial neural networks (ANNs), neural computation is abstracted to an activation function that is usually shared between all neurons within a layer or even the whole network; training of ANNs focuses on synaptic optimization. In this paper, we propose the optimization of neuro-centric parameters to attain a set of diverse neurons that can perform complex computations. Demonstrating the promise of the approach, we show that evolving neural parameters alone allows agents to solve various reinforcement learning tasks without optimizing any synaptic weights. While not aiming to be an accurate biological model, parameterizing neurons to a larger degree than the current common practice, allows us to ask questions about the computational abilities afforded by neural diversity in random neural networks. The presented results open up interesting future research directions, such as combining evolved neural diversity with activity-dependent plasticity.
AI-11-标题: A Diagnosis Algorithms for a Rotary Indexing Machine
作者: Maria Krantz, Oliver Niggemann
Abstract: Rotary Indexing Machines (RIMs) are widely used in manufacturing due to their ability to perform multiple production steps on a single product without manual repositioning, reducing production time and improving accuracy and consistency. Despite their advantages, little research has been done on diagnosing faults in RIMs, especially from the perspective of the actual production steps carried out on these machines. Long downtimes due to failures are problematic, especially for smaller companies employing these machines. To address this gap, we propose a diagnosis algorithm based on the product perspective, which focuses on the product being processed by RIMs. The algorithm traces the steps that a product takes through the machine and is able to diagnose possible causes in case of failure. We also analyze the properties of RIMs and how these influence the diagnosis of faults in these machines. Our contributions are three-fold. Firstly, we provide an analysis of the properties of RIMs and how they influence the diagnosis of faults in these machines. Secondly, we suggest a diagnosis algorithm based on the product perspective capable of diagnosing faults in such a machine. Finally, we test this algorithm on a model of a rotary indexing machine, demonstrating its effectiveness in identifying faults and their root causes.
AI-12-标题: Towards a Capability Assessment Model for the Comprehension and Adoption of AI in Organisations
作者: Butler, Tom, Espinoza-Limón, Angelina, Seppälä, Selja
Abstract: The comprehension and adoption of Artificial Intelligence (AI) are beset with practical and ethical problems. This article presents a 5-level AI Capability Assessment Model (AI-CAM) and a related AI Capabilities Matrix (AI-CM) to assist practitioners in AI comprehension and adoption. These practical tools were developed with business executives, technologists, and other organisational stakeholders in mind. They are founded on a comprehensive conception of AI compared to those in other AI adoption models and are also open-source artefacts. Thus, the AI-CAM and AI-CM present an accessible resource to help inform organisational decision-makers on the capability requirements for (1) AI-based data analytics use cases based on machine learning technologies; (2) Knowledge representation to engineer and represent data, information and knowledge using semantic technologies; and (3) AI-based solutions that seek to emulate human reasoning and decision-making. The AI-CAM covers the core capability dimensions (business, data, technology, organisation, AI skills, risks, and ethical considerations) required at the five capability maturity levels to achieve optimal use of AI in organisations.
AI-13-标题: Learning Assumption-based Argumentation Frameworks
作者: Maurizio Proietti, Francesca Toni
Abstract: We propose a novel approach to logic-based learning which generates assumption-based argumentation (ABA) frameworks from positive and negative examples, using a given background knowledge. These ABA frameworks can be mapped onto logic programs with negation as failure that may be non-stratified. Whereas existing argumentation-based methods learn exceptions to general rules by interpreting the exceptions as rebuttal attacks, our approach interprets them as undercutting attacks. Our learning technique is based on the use of transformation rules, including some adapted from logic program transformation rules (notably folding) as well as others, such as rote learning and assumption introduction. We present a general strategy that applies the transformation rules in a suitable order to learn stratified frameworks, and we also propose a variant that handles the non-stratified case. We illustrate the benefits of our approach with a number of examples, which show that, on one hand, we are able to easily reconstruct other logic-based learning approaches and, on the other hand, we can work out in a very simple and natural way problems that seem to be hard for existing techniques.
AI-14-标题: A Fast Algorithm for Consistency Checking Partially Ordered Time
作者: Leif Eriksson, Victor Lagerkvist
Abstract: Partially ordered models of time occur naturally in applications where agents or processes cannot perfectly communicate with each other, and can be traced back to the seminal work of Lamport. In this paper we consider the problem of deciding if a (likely incomplete) description of a system of events is consistent, the network consistency problem for the point algebra of partially ordered time (POT). While the classical complexity of this problem has been fully settled, comparably little is known of the fine-grained complexity of POT except that it can be solved in O^((0.368n)^n) time by enumerating ordered partitions. We construct a much faster algorithm with a run-time bounded by O^((0.26n)^n) . This is achieved by a sophisticated enumeration of structures similar to total orders, which are then greedily expanded toward a solution. While similar ideas have been explored earlier for related problems it turns out that the analysis for POT is non-trivial and requires significant new ideas.
AI-15-标题: ChatGPT for PLC/DCS Control Logic Generation
作者: Heiko Koziolek, Sten Gruener, Virendra Ashiwal
备注: 8 pages, 6 figures
Abstract: Large language models (LLMs) providing generative AI have become popular to support software engineers in creating, summarizing, optimizing, and documenting source code. It is still unknown how LLMs can support control engineers using typical control programming languages in programming tasks. Researchers have explored GitHub CoPilot or DeepMind AlphaCode for source code generation but did not yet tackle control logic programming. The contribution of this paper is an exploratory study, for which we created 100 LLM prompts in 10 representative categories to analyze control logic generation for of PLCs and DCS from natural language. We tested the prompts by generating answers with ChatGPT using the GPT-4 LLM. It generated syntactically correct IEC 61131-3 Structured Text code in many cases and demonstrated useful reasoning skills that could boost control engineer productivity. Our prompt collection is the basis for a more formal LLM benchmark to test and compare such models for control logic generation.
AI-16-标题: Service Composition in the ChatGPT Era
作者: Marco Aiello, Ilche Georgievski
Abstract: The paper speculates about how ChatGPT-like systems can support the field of automated service composition and identifies new research areas to explore in order to take advantage of such tools in the field of service-oriented composition.
AI-17-标题: On the Planning Abilities of Large Language Models – A Critical Investigation
作者: Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao Kambhampati
备注: arXiv admin note: text overlap with arXiv:2302.06706
Abstract: Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs as a source of heuristic guidance for other agents (AI planners) in their planning tasks. We conduct a systematic study by generating a suite of instances on domains similar to the ones employed in the International Planning Competition and evaluate LLMs in two distinct modes: autonomous and heuristic. Our findings reveal that LLMs’ ability to generate executable plans autonomously is rather limited, with the best model (GPT-4) having an average success rate of ~12% across the domains. However, the results in the heuristic mode show more promise. In the heuristic mode, we demonstrate that LLM-generated plans can improve the search process for underlying sound planners and additionally show that external verifiers can help provide feedback on the generated plans and back-prompt the LLM for better plan generation.
AI-18-标题: TransWorldNG: Traffic Simulation via Foundation Model
作者: Ding Wang, Xuhong Wang, Liang Chen, Shengyue Yao, Ming Jing, Honghai Li, Li Li, Shiqiang Bao, Fei-Yue Wang, Yilun Lin
Abstract: Traffic simulation is a crucial tool for transportation decision-making and policy development. However, achieving realistic simulations in the face of the high dimensionality and heterogeneity of traffic environments is a longstanding challenge. In this paper, we present TransWordNG, a traffic simulator that uses Data-driven algorithms and Graph Computing techniques to learn traffic dynamics from real data. The functionality and structure of TransWorldNG are introduced, which utilize a foundation model for transportation management and control. The results demonstrate that TransWorldNG can generate more realistic traffic patterns compared to traditional simulators. Additionally, TransWorldNG exhibits better scalability, as it shows linear growth in computation time as the scenario scale increases. To the best of our knowledge, this is the first traffic simulator that can automatically learn traffic patterns from real-world data and efficiently generate accurate and realistic traffic environments.
AI-19-标题: Analysis and tuning of a three-term DMC
作者: Yun Zhu, Kangkang Zhang, Yuncai Zhu, Jinming Zhou
备注: 16 pages, 14 figures
Abstract: Most MPC (Model Predictive Control) algorithms used in industries and studied in the control academia use a two-term QP (quadratic programming), where the first term is the weighted norm of the output errors, and the second term is that of the input increments. In this work, a DMC (Dynamic Matrix Control) algorithm that uses three-term QP is studied, where the third term is the weighted norm of the output increments. In the analysis, a relationship between the three-term DMC and the two-term DMC is established; based on that, the closed-loop response curves are derived. Based on the analysis, two controller tuning procedures are developed for the three-term DMC, one for closed-loop step response and one for disturbance reduction. Finally, it will be proven that the three-term DMC can achieve a higher performance and robustness than the two-term DMC can. Simulation studies are used to demonstrate the findings and the tuning methods.
AI-20-标题: Rethink Diversity in Deep Learning Testing
作者: Zi Wang, Jihye Choi, Somesh Jha
Abstract: Deep neural networks (DNNs) have demonstrated extraordinary capabilities and are an integral part of modern software systems. However, they also suffer from various vulnerabilities such as adversarial attacks and unfairness. Testing deep learning (DL) systems is therefore an important task, to detect and mitigate those vulnerabilities. Motivated by the success of traditional software testing, which often employs diversity heuristics, various diversity measures on DNNs have been proposed to help efficiently expose the buggy behavior of DNNs. In this work, we argue that many DNN testing tasks should be treated as directed testing problems rather than general-purpose testing tasks, because these tasks are specific and well-defined. Hence, the diversity-based approach is less effective. Following our argument based on the semantics of DNNs and the testing goal, we derive 6 metrics that can be used for DNN testing and carefully analyze their application scopes. We empirically show their efficacy in exposing bugs in DNNs compared to recent diversity-based metrics. Moreover, we also notice discrepancies between the practices of the software engineering (SE) community and the DL community. We point out some of these gaps, and hopefully, this can lead to bridging the SE practice and DL findings.
AI-21-标题: Privacy Protectability: An Information-theoretical Approach
作者: Siping Shi, Bihai Zhang, Dan Wang
Abstract: Recently, inference privacy has attracted increasing attention. The inference privacy concern arises most notably in the widely deployed edge-cloud video analytics systems, where the cloud needs the videos captured from the edge. The video data can contain sensitive information and subject to attack when they are transmitted to the cloud for inference. Many privacy protection schemes have been proposed. Yet, the performance of a scheme needs to be determined by experiments or inferred by analyzing the specific case. In this paper, we propose a new metric, \textitprivacy protectability, to characterize to what degree a video stream can be protected given a certain video analytics task. Such a metric has strong operational meaning. For example, low protectability means that it may be necessary to set up an overall secure environment. We can also evaluate a privacy protection scheme, e.g., assume it obfuscates the video data, what level of protection this scheme has achieved after obfuscation. Our definition of privacy protectability is rooted in information theory and we develop efficient algorithms to estimate the metric. We use experiments on real data to validate that our metric is consistent with empirical measurements on how well a video stream can be protected for a video analytics task.
AI-22-标题: Asking Before Action: Gather Information in Embodied Decision Making with Language Models
作者: Xiaoyu Chen, Shenao Zhang, Pushi Zhang, Li Zhao, Jianyu Chen
Abstract: With strong capabilities of reasoning and a generic understanding of the world, Large Language Models (LLMs) have shown great potential in building versatile embodied decision making agents capable of performing diverse tasks. However, when deployed to unfamiliar environments, we show that LLM agents face challenges in efficiently gathering necessary information, leading to suboptimal performance. On the other hand, in unfamiliar scenarios, human individuals often seek additional information from their peers before taking action, leveraging external knowledge to avoid unnecessary trial and error. Building upon this intuition, we propose \textitAsking Before Action (ABA), a method that empowers the agent to proactively query external sources for pertinent information using natural language during their interactions in the environment. In this way, the agent is able to enhance its efficiency and performance by mitigating wasteful steps and circumventing the difficulties associated with exploration in unfamiliar environments. We empirically evaluate our method on an embodied decision making benchmark, ALFWorld, and demonstrate that despite modest modifications in prompts, our method exceeds baseline LLM agents by more than 40 %. Further experiments on two variants of ALFWorld illustrate that by imitation learning, ABA effectively retains and reuses queried and known information in subsequent tasks, mitigating the need for repetitive inquiries. Both qualitative and quantitative results exhibit remarkable performance on tasks that previous methods struggle to solve.
AI-23-标题: Learning-Based Automatic Synthesis of Software Code and Configuration
作者: Shantanu Mandal
备注: arXiv admin note: text overlap with arXiv:2211.00828
Abstract: Increasing demands in software industry and scarcity of software engineers motivates researchers and practitioners to automate the process of software generation and configuration. Large scale automatic software generation and configuration is a very complex and challenging task. In this proposal, we set out to investigate this problem by breaking down automatic software generation and configuration into two different tasks. In first task, we propose to synthesize software automatically with input output specifications. This task is further broken down into two sub-tasks. The first sub-task is about synthesizing programs with a genetic algorithm which is driven by a neural network based fitness function trained with program traces and specifications. For the second sub-task, we formulate program synthesis as a continuous optimization problem and synthesize programs with covariance matrix adaption evolutionary strategy (a state-of-the-art continuous optimization method). Finally, for the second task, we propose to synthesize configurations of large scale software from different input files (e.g. software manuals, configurations files, online blogs, etc.) using a sequence-to-sequence deep learning mechanism.
AI-24-标题: Distributed Online Rollout for Multivehicle Routing in Unmapped Environments
作者: Jamison W. Weber, Dhanush R. Giriyan, Devendra R. Parkar, Andréa W. Richa, Dimitri P. Bertsekas
Abstract: In this work we consider a generalization of the well-known multivehicle routing problem: given a network, a set of agents occupying a subset of its nodes, and a set of tasks, we seek a minimum cost sequence of movements subject to the constraint that each task is visited by some agent at least once. The classical version of this problem assumes a central computational server that observes the entire state of the system perfectly and directs individual agents according to a centralized control scheme. In contrast, we assume that there is no centralized server and that each agent is an individual processor with no a priori knowledge of the underlying network (including task and agent locations). Moreover, our agents possess strictly local communication and sensing capabilities (restricted to a fixed radius around their respective locations), aligning more closely with several real-world multiagent applications. These restrictions introduce many challenges that are overcome through local information sharing and direct coordination between agents. We present a fully distributed, online, and scalable reinforcement learning algorithm for this problem whereby agents self-organize into local clusters and independently apply a multiagent rollout scheme locally to each cluster. We demonstrate empirically via extensive simulations that there exists a critical sensing radius beyond which the distributed rollout algorithm begins to improve over a greedy base policy. This critical sensing radius grows proportionally to the \log^* function of the size of the network, and is, therefore, a small constant for any relevant network. Our decentralized reinforcement learning algorithm achieves approximately a factor of two cost improvement over the base policy for a range of radii bounded from below and above by two and three times the critical sensing radius, respectively.
AI-25-标题: From Interactive to Co-Constructive Task Learning ICRA2023
作者: Anna-Lisa Vollmer, Daniel Leidner, Michael Beetz, Britta Wrede
备注: 7 pages, 1 figure, accepted to ICRA 2023 Workshop ‘Life-Long Learning with Human Help’ (L3H2)
Abstract: Humans have developed the capability to teach relevant aspects of new or adapted tasks to a social peer with very few task demonstrations by making use of scaffolding strategies that leverage prior knowledge and importantly prior joint experience to yield a joint understanding and a joint execution of the required steps to solve the task. This process has been discovered and analyzed in parent-infant interaction and constitutes a ``co-construction’’ as it allows both, the teacher and the learner, to jointly contribute to the task. We propose to focus research in robot interactive learning on this co-construction process to enable robots to learn from non-expert users in everyday situations. In the following, we will review current proposals for interactive task learning and discuss their main contributions with respect to the entailing interaction. We then discuss our notion of co-construction and summarize research insights from adult-child and human-robot interactions to elucidate its nature in more detail. From this overview we finally derive research desiderata that entail the dimensions architecture, representation, interaction and explainability.
AI-26-标题: Trends and Challenges Towards an Effective Data-Driven Decision Making in UK SMEs: Case Studies and Lessons Learnt from the Analysis of 85 SMEs
作者: Abdel-Rahman Tawil, Muhidin Mohamed, Xavier Schmoor, Konstantinos Vlachos, Diana Haidar
Abstract: The adoption of data science brings vast benefits to Small and Medium-sized Enterprises (SMEs) including business productivity, economic growth, innovation and jobs creation. Data Science can support SMEs to optimise production processes, anticipate customers’ needs, predict machinery failures and deliver efficient smart services. Businesses can also harness the power of Artificial Intelligence (AI) and Big Data and the smart use of digital technologies to enhance productivity and performance, paving the way for innovation. However, integrating data science decisions into an SME requires both skills and IT investments. In most cases, such expenses are beyond the means of SMEs due to limited resources and restricted access to financing. This paper presents trends and challenges towards an effective data-driven decision making for organisations based on a case study of 85 SMEs, mostly from the West Midlands region of England. The work is supported as part of a 3 years ERDF (European Regional Development Funded project) in the areas of big data management, analytics and business intelligence. We present two case studies that demonstrates the potential of Digitisation, AI and Machine Learning and use these as examples to unveil challenges and showcase the wealth of current available opportunities for SMEs.
AI-27-标题: DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion
作者: Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee
备注: 23 pages, 10 figures, 17 tables, under review
Abstract: Diffusion-based generative models have exhibited powerful generative performance in recent years. However, as many attributes exist in the data distribution and owing to several limitations of sharing the model parameters across all levels of the generation process, it remains challenging to control specific styles for each attribute. To address the above problem, this paper presents decoupled denoising diffusion models (DDDMs) with disentangled representations, which can control the style for each attribute in generative models. We apply DDDMs to voice conversion (VC) tasks to address the challenges of disentangling and controlling each speech attribute (e.g., linguistic information, intonation, and timbre). First, we use a self-supervised representation to disentangle the speech representation. Subsequently, the DDDMs are applied to resynthesize the speech from the disentangled representations for denoising with respect to each attribute. Moreover, we also propose the prior mixup for robust voice style transfer, which uses the converted representation of the mixed style as a prior distribution for the diffusion models. The experimental results reveal that our method outperforms publicly available VC models. Furthermore, we show that our method provides robust generative performance regardless of the model size. Audio samples are available this https URL.
AI-28-标题: Inverse square Levy walk emerging universally in goal-oriented tasks
作者: Shuji Shinohara, Daiki Morita, Nobuhito Manome, Ryota Hayashi, Toru Moriyama, Hiroshi Okamoto, Pegio-Yukio Gunji, Ung-il Chung
Abstract: The Levy walk in which the frequency of occurrence of step lengths follows a power-law distribution, can be observed in the migratory behavior of organisms at various levels. Levy walks with power exponents close to 2 are observed, and the reasons are unclear. This study aims to propose a model that universally generates inverse square Levy walks (called Cauchy walks) and to identify the conditions under which Cauchy walks appear. We demonstrate that Cauchy walks emerge universally in goal-oriented tasks. We use the term “goal-oriented” when the goal is clear, but this can be achieved in different ways, which cannot be uniquely determined. We performed a simulation in which an agent observed the data generated from a probability distribution in a two-dimensional space and successively estimated the central coordinates of that probability distribution. The agent has a model of probability distribution as a hypothesis for data-generating distribution and can modify the model such that each time a data point is observed, thereby increasing the estimated probability of occurrence of the observed data. To achieve this, the center coordinates of the model must be close to those of the observed data. However, in the case of a two-dimensional space, arbitrariness arises in the direction of correction of the center; this task is goal oriented. We analyze two cases: a strategy that allocates the amount of modification randomly in the x- and y-directions, and a strategy that determines allocation such that movement is minimized. The results reveal that when a random strategy is used, the frequency of occurrence of the movement lengths shows a power-law distribution with exponent 2. When the minimum strategy is used, the Brownian walk appears. The presence or absence of the constraint of minimizing the amount of movement may be a factor that causes the difference between Brownian and Levy walks.