检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Wang, Shuai Chen, Zhengyang Han, Bing Wang, Hongji Liang, Chengdong Zhang, Binbin Xiang, Xu Ding, Wen Rohdin, Johan Silnova, Anna Qian, Yanmin Li, Haizhou Shenzhen Institute of Big Data Guangdong Shenzhen China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China Horizon Robotics Beijing China NVIDIA Shanghai China Brno University of Technology Faculty of Information Technology IT4I Centre of Excellence Czech Republic School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen China

Speaker modeling plays a crucial role in various tasks, and fixed-dimensional vector representations, known as speaker embeddings, are the predominant modeling approach. These embeddings are typically evaluated within the framework of speaker verification, yet their utility extends to a broad scope of related tasks including speaker diarization, speech synthesis, voice conversion, and target speaker extraction. This paper presents Wespeaker, a user-friendly toolkit designed for both research and production purposes, dedicated to the learning of speaker embeddings. Wespeaker offers scalable data management, state-of-the-art speaker embedding models, and self-supervised learning training schemes with the potential to leverage large-scale unlabeled real-world data. The toolkit incorporates structured recipes that have been successfully adopted in winning systems across various speaker verification challenges, ensuring highly competitive results. For production-oriented development, Wespeaker integrates CPU- and GPUcompatible deployment and runtime codes, supporting mainstream platforms such as Windows, Linux, Mac and on-device chips such as horizon X3’PI. Wespeaker also provides off-the-shelf high-quality speaker embeddings by providing various pretrained models, which can be effortlessly applied to different tasks that require speaker modeling. The toolkit is publicly available at https://***/wenet-e2e/wespeaker. © 2024, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

arXiv

引用

arXiv 2023年

作者： Zhou, Ziqi Hu, Shengshan Zhao, Ruizhi Wang, Qian Zhang, Leo Yu Hou, Junhui Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Wuhan University China School of Information and Communication Technology Griffith University Australia Department of Computer Science City University of Hong Kong Hong Kong National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China 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 use. In 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://github. com/CGCL-codes/AdvEncoder. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Group RandAugment: Video Augmentation for Action Recognition 5

Group RandAugment: Video Augmentation for Action Recognition

引用

5th International Conference on data science and Information Technology, DSIT 2022

作者： An, Fengmin Zhang, Bingbing Wang, Zhenwei Dong, Wei Zhang, Jianxin School of Computer Science and Engineering Dalian Minzu University Dalian China Institute of Machine Intelligence and Bio-computing Dalian Minzu University Dalian China SEAC Key Lab of Big Data Applied Technology Dalian Minzu University Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

data augmentation, as a critical strategy in deep learning, well improves the sample diversity for network training, leading to the obvious improvement of model generalization ability. Besides, automatic data augmentation, while sparking in image tasks, has attracted too little attention in video recognition task. Therefore, this work explores a novel group random augmentation (GRA) that automatically augments video data for recognition. GRA first collects 21 augmentation transformations to enrich the sample diversity, and then divides these transformations into four groups (i.e., pixel-transform, rigidtransform, erasing-transform, environment-transform) to reduce the excessive regularization caused by similar augmentation. To reduce the computational cost of finding the optimal setting, GRA adopts the combination form to select the optimal situation. For frames in the same video clip, GRA uses synchronous GRA. Additionally, the proposed GRA can be integrated into any existing video frameworks. To prove the effectiveness of GRA, we conduct experiments on two commonly used video action recognition benchmarks (Something-Something V1 & V2) and three typical frameworks (TSM, GSM, and TEA), whose results demonstrate GRA can improve performance in all cases without adding additional computational cost. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Full-atom protein pocket design via iterative refinement 23

Full-atom protein pocket design via iterative refinement

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zaixi Zhang Zepu Lu Zhongkai Hao Marinka Zitnik Qi Liu Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China and Harvard University Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua-Bosch Joint ML Center Tsinghua Harvard University

The design and optimization of functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10% in AAR and RMSD metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm’s generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

arXiv

引用

arXiv 2022年

作者： Hu, Xin Zhang, Lingling Liu, Jun Fan, Jinfu You, Yang Wu, Yaqiang Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University China Department of Control Science and Engineering Tongji University Shanghai China Department of Computer Science National University of Singapore Singapore Lenovo Research Beijing China

Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architecture. Gestalt perception contains a series of laws to explain human perception, that the human visual system tends to perceive patches in an image that are similar, close or connected without abrupt directional changes as a perceptual whole object. Inspired by these thoughts, we build a gestalt-perception graph in transformer encoder, which is composed of diagram patches as nodes and the relationships between patches as edges. This graph aims to group these patches into objects via laws of similarity, proximity, and smoothness implied in these edges, so that the meaningful objects can be effectively detected. The experimental results demonstrate that the proposed GPTR achieves the best results in the diagram object detection task. Our model also obtains comparable results over the competitors in natural image object detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics

arXiv

引用

arXiv 2024年

作者： Wu, Liming Hou, Zhichao Yuan, Jirui Rong, Yu Huang, Wenbing Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science North Carolina State University United States Tsinghua University China Tencent AI Lab China

Learning to represent and simulate the dynamics of physical systems is a crucial yet challenging task. Existing equivariant Graph Neural Network (GNN) based methods have encapsulated the symmetry of physics, e.g., translations, rotations, etc, leading to better generalization ability. Nevertheless, their frame-to-frame formulation of the task overlooks the non-Markov property mainly incurred by unobserved dynamics in the environment. In this paper, we reformulate dynamics simulation as a spatio-temporal prediction task, by employing the trajectory in the past period to recover the Non-Markovian interactions. We propose Equivariant Spatio-Temporal Attentive Graph Networks (ESTAG), an equivariant version of spatio-temporal GNNs, to fulfill our purpose. At its core, we design a novel Equivariant Discrete Fourier Transform (EDFT) to extract periodic patterns from the history frames, and then construct an Equivariant Spatial Module (ESM) to accomplish spatial message passing, and an Equivariant Temporal Module (ETM) with the forward attention and equivariant pooling mechanisms to aggregate temporal message. We evaluate our model on three real datasets corresponding to the molecular-, protein- and macro-level. Experimental results verify the effectiveness of ESTAG compared to typical spatio-temporal GNNs and equivariant GNNs. Copyright © 2024, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

引用

Design Automation Conference

作者： Jin Zhao Yu Zhang Jian Cheng Yiyang Wu Chuyue Ye Hui Yu Zhiying Huang Hai Jin Xiaofei Liao Lin Gu Haikun Liu National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Zhejiang-HUST Joint Research Center for Graph Processing Zhejiang Lab Hangzhou China

Temporal graph processing is used to handle the snapshots of the temporal graph, which concerns changes in graph over time. Although several software/hardware solutions have been designed for efficient temporal graph processing, they still suffer from serious irregular data access due to the uncoordinated graph traversal. To overcome these limitations, this paper proposes SaGraph, a domain-specific hardware accelerator to support the efficient processing of temporal graph. Specifically, temporal graph processing shows strong data access similarity, i.e., most graph accesses of the processing of different snapshots are the same and usually refer to a small fraction of vertices. SaGraph can dynamically coordinate the graph traversals and adaptively cache the vertex states to fully exploit the data access similarity for smaller data access overhead. We implemented and evaluated SaGraph on a Xilinx Alveo U280 FPGA card. Compared with the cutting-edge software and hardware solutions, SaGraph achieves 8.5×-157.3×, 4.2×-16.1× speedups and 34.7×-423.6×, 5.3×-14.7× energy savings, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-links matter for link prediction: rethinking the debiased GNN from a data perspective 23

Cross-links matter for link prediction: rethinking the debia...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zihan Luo Hong Huang Jianxun Lian Xiran Song Xing Xie Hai Jin National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Microsoft Research Asia Beijing China

Recently, the bias-related issues in GNN-based link prediction have raised widely spread concerns. In this paper, we emphasize the bias on links across different node clusters, which we call cross-links, after considering its significance in both easing information cocoons and preserving graph connectivity. Instead of following the objective-oriented mechanism in prior works with compromised utility, we empirically find that existing GNN models face severe data bias between internal-links (links within the same cluster) and cross-links, and this inspires us to rethink the bias issue on cross-links from a data perspective. Specifically, we design a simple yet effective twin-structure framework, which can be easily applied to most GNNs to mitigate the bias as well as boost their utility in an end-to-end manner. The basic idea is to generate debiased node embeddings as demonstrations and fuse them into the embeddings of original GNNs. In particular, we learn debiased node embeddings with the help of augmented supervision signals, and a novel dynamic training strategy is designed to effectively fuse debiased node embeddings with the original node embeddings. Experiments on three datasets with six common GNNs show that our framework can not only alleviate the bias between internal-links and cross-links but also boost the overall accuracy. Comparisons with other state-of-the-art methods also verify the superiority of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning

arXiv

引用

arXiv 2024年

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Our code is available at https://***/Gp1g/FedAA. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：