检索结果-内蒙古大学图书馆

GNOTHI SEAUTON: EMPOWERING FAITHFUL SELF-INTERPRETABILITY IN BLACK-BOX TRANSFORMERS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shaobo Tang, Hongxuan Wang, Mingyang Zhang, Hongrui Liu, Xuyang Li, Weiya Hu, Xuming Zhang, Linfeng School of Artificial Intelligence Shanghai Jiao Tong University China Efficient and Precision Intelligent Computing Lab Shanghai Jiao Tong University China Sichuan University China Big Data and AI Lab ICBC Hong Kong University of Science and Technology Guangzhou China

The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable concepts but often struggle with performance and scalability. Conversely, post-hoc methods like Shapley values, while theoretically robust, are computationally expensive and resource-intensive. To bridge the gap between these two lines of research, we propose a novel method that combines their strengths, providing theoretically guaranteed self-interpretability for black-box models without compromising prediction accuracy. Specifically, we introduce a parameter-efficient pipeline, AutoGnothi, which integrates a small side network into the black-box model, allowing it to generate Shapley value explanations without changing the original network parameters. This side-tuning approach significantly reduces memory, training, and inference costs, outperforming traditional parameter-efficient methods, where full fine-tuning serves as the optimal baseline. AutoGnothi enables the black-box model to predict and explain its predictions with minimal overhead. Extensive experiments show that AutoGnothi offers accurate explanations for both vision and language tasks, delivering superior computational efficiency with comparable interpretability. © 2024, CC BY.

关键词： Economic and social effects

How Graph Neural Networks Learn: Lessons from Training Dynamics

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Chenxiao Wu, Qitian Wipf, David Sun, Ruoyu Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University China Amazon Web Services United States School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call kernel-graph alignment. We provide theoretical explanations for the emergence of this phenomenon in the overparameterized regime and empirically validate it on real-world GNNs. This finding offers new interpretable insights into when and why the learned GNN functions generalize, highlighting their limitations in heterophilic graphs. Practically, we propose a parameter-free algorithm that directly uses a sparse matrix (i.e. graph adjacency) to update the learned function. We demonstrate that this embarrassingly simple approach can be as effective as GNNs while being orders-of-magnitude faster. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Robust Cross-Domain Speaker Verification with Multi-Level Domain Adapters

学校读者我要写书评

暂无评论

Robust Cross-Domain Speaker Verification with Multi-Level Do...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wen Huang Bing Han Shuai Wang Zhengyang Chen Yanmin Qian AI Institute Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

Speaker verification encounters significant challenges when confronted with diverse domain data, often resulting in performance degradation due to domain mismatch. To enhance performance in cross-domain scenarios, we introduce the Domain Adapter, an adaptable module designed for specific domains. This module learns and integrates domain-specific information with speaker-related data, mitigating domain-related variations and promoting convergence of utterance embeddings from the same speaker across diverse domains. It offers configurability across multiple levels and is adaptable to various backbone architectures. Our proposed module substantially enhances cross-domain performance with minimal parameter increments while effectively generalizing to previously unseen domains. In our experiments, we present results on the 3D-Speaker dataset, which provides acoustically-relevant attributes crucial for domain categorization and the subsequent learning of domain information. The top-performing system integrated with domain adapters achieved 10.8%, 14.8%, and 21.1% EER improvements over the baseline across three 3D-Speaker dataset trials.

关键词：

Downstream-agnostic Adversarial Examples

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

International Conference on Computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Meng, Qingyan Xiao, Mingqing Yan, Shen Wang, Yisen Lin, Zhouchen Luo, Zhi-Quan The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China National Key Lab. of General AI School of Intelligence Science and Technology Peking University China Center for Data Science Peking University China Institute for Artificial Intelligence Peking University China Peng Cheng Laboratory China

Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN methods, the backpropagation through time (BPTT) with surrogate gradients (SG) method has achieved high performance. However, this method suffers from considerable memory cost and training time during training. In this paper, we propose the Spatial Learning Through Time (SLTT) method that can achieve high performance while greatly improving training efficiency compared with BPTT. First, we show that the backpropagation of SNNs through the temporal domain contributes just a little to the final calculated gradients. Thus, we propose to ignore the unimportant routes in the computational graph during backpropagation. The proposed method reduces the number of scalar multiplications and achieves a small memory occupation that is independent of the total time steps. Furthermore, we propose a variant of SLTT, called SLTT-K, that allows backpropagation only at K time steps, then the required number of scalar multiplications is further reduced and is independent of the total time steps. Experiments on both static and neuromorphic datasets demonstrate superior training efficiency and performance of our SLTT. In particular, our method achieves state-of-the-art accuracy on ImageNet, while the memory cost and training time are reduced by more than 70% and 50%, respectively, compared with BPTT. Our code is available at https://***/qymeng94/SLTT. Copyright © 2023, The Authors. All rights reserved.

关键词： Backpropagation

Adaptive Context Selection for Polyp Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Ruifei Li, Guanbin Li, Zhen Cui, Shuguang Qian, Dahong Yu, Yizhou School of Data and Computer Science Sun Yat-sen University Guangzhou China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Deepwise Ai Lab Beijing China

Accurate polyp segmentation is of great significance for the diagnosis and treatment of colorectal cancer. However, it has always been very challenging due to the diverse shape and size of polyp. In recent years, state-of-the-art methods have achieved significant breakthroughs in this task with the help of deep convolutional neural networks. However, few algorithms explicitly consider the impact of the size and shape of the polyp and the complex spatial context on the segmentation performance, which results in the algorithms still being powerless for complex samples. In fact, segmentation of polyps of different sizes relies on different local and global contextual information for regional contrast reasoning. To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM). Specifically, LCA modules deliver local context features from encoder layers to decoder layers, enhancing the attention to the hard region which is determined by the prediction map of previous layer. GCM aims to further explore the global context features and send to the decoder layers. ASM is used for adaptive selection and aggregation of context features through channel-wise attention. Our proposed approach is evaluated on the EndoScene and Kvasir-SEG datasets, and shows outstanding performance compared with other state-of-the-art methods. The code is available at https://***/ReaFly/ACSNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit 48

学校读者我要写书评

暂无评论

Wespeaker: A Research and Production Oriented Speaker Embedd...

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Hongji Liang, Chengdong Wang, Shuai Chen, Zhengyang Zhang, Binbin Xiang, Xu Deng, Yanlei Qian, Yanmin Shanghai Jiao Tong University MoE Key Lab of Ai X-LANCE Lab Cse Dept Shanghai China Tencent Corporation Tencent Ethereal Audio Lab Shenzhen China WeNet Open Source Community Northwestern Polytechnical University School of Marine Science and Technology Xi'an China Nvidia Santa Clara United States The Chinese University of HongKong Shenzhen Research Institute of Big Data Shenzhen China Horizon Robotics Beijing China AISpeech Ltd Suzhou China

ISBN: (纸本)9781728163277

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://***/wenet-e2e/wespeaker. © 2023 IEEE.

关键词： Embeddings

NC-ALG: Graph-Based Active Learning Under Noisy Crowd

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active Learning Under Noisy Crowd

International Conference on data Engineering

作者： Wentao Zhang Yexin Wang Zhenbang You Yang Li Gang Cao Zhi Yang Bin Cui Center for Machine Learning Research Peking University Institute of Advanced Algorithms Research Shanghai National Engineering Labratory for Big Data Analytics and Applications Key Lab of High Confidence Software Technologies Peking University Department of Data Platform TEG Tencent Inc. Beijing Academy of Artificial Intelligence Institute of Computational Social Science Peking University Qingdao

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active Learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed.

关键词： Crowdsourcing Costs Noise Predictive models Graph neural networks labeling Noise measurement

Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Wen Han, Bing Chen, Zhengyang Wang, Shuai Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain adaptation scenarios where some unlabeled target domain data is available. However, these methods often have limited performance improvement and lack generalization in various mismatch situations. In this paper, we propose Prototype and Instance Contrastive Learning (PICL), a novel method for unsupervised domain adaptation in speaker verification through dual-level contrastive learning. For prototype contrastive learning, we generate pseudo labels via clustering to create dynamically updated prototype representations, aligning instances with their corresponding class or cluster prototypes. For instance contrastive learning, we minimize the distance between different views or augmentations of the same instance, ensuring robust and invariant representations resilient to variations like noise. This dual-level approach provides both high-level and low-level supervision, leading to improved generalization and robustness of the speaker verification model. Unlike previous studies that only evaluated mismatches in one situation, we have conducted relevant explorations on various datasets and achieved state-of-the-art performance currently, which also proves the generalization of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning