检索结果-内蒙古大学图书馆

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

作者： Yang, Liu Jiang, Yu Hong, Junkun Wu, Zhenjie Yang, Zhan Long, Jun Central South University School of Computer Science and Engineering China Central South University Big Data Institute Central South University China Central South University Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province Changsha China

ISBN: (纸本)9781728163277

Action segmentation plays an important role in video understanding, which is implemented by frame-wise action classification. Recent works on action segmentation capture long-term dependencies by increasing temporal convolution layers in Temporal Convolution Networks (TCNs). However, high layers in TCNs are more coarse access to video features, resulting in the loss of fine-grained information for frame-wise action classification. To address the above issues, we propose a novel Attention-based Temporal Convolution (ATC) block to capture fine-grained information of temporal dependencies for frame-wise action classification by self-attention mechanism. Via stacking ATC blocks, we design a Stacking-based Attention Temporal Convolutional Network (SATC) to adaptively capture long-term and short-term dependencies, according to the semantic similarity of features on different temporal receptive fields simultaneously. The experimental results demonstrate that our SATC outperforms other baselines on all three challenging datasets: GTEA, 50Salads and Breakfast. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Medical Treatment Process Modeling Based on Process Mining and Treatment Patterns

引用

China Communications 2021年第12期18卷 332-349页

作者： Liqin Yang Guosheng Kang Liang Zhang School of Computer Science Fudan UniversityShanghai 200438China Shanghai Key Laboratory of Data Science Shanghai 200438China Institute of Intelligent Electronics and Systems Shanghai 200438China Computer Teaching and Research Section Shanghai University of Traditional Chinese MedicineShanghai 201203China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan 411201China

***-periments on a synthetic log of the non-secondary hy-pertension MTP and empirical findings demonstrate the effectiveness of our *** results show that the process mining in our approach framework can automatically generate more accurate MTP mod-els,and the subprocess models based on treatment pat-terns make the models easy to understand.

关键词： business process modeling medical treat-ment processes treatment patterns clinical practice guidelines

来源：评论

学校读者我要写书评

暂无评论

Max-and-Min Fractional Programming for Communications and Sensing

Max-and-Min Fractional Programming for Communications and Se...

引用

IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

作者： Yannan Chen Licheng Zhao Kaiming Shen School of Science and Engineering The Chinese University of Hong Kong (Shenzhen) China Shenzhen Research Institute of Big Data China

There is considerable interest in the use of fractional programming (FP) for the communication system design because many problems in this area are fractionally structured. Notably, max-FP and min-FP are not interchangeable in general if there are multiple ratios, so the two types of FP are often dealt with separately in the existing literature. As a result, an FP method for maximizing the signal-to-interference-plus-noise ratios (SINRs) typically cannot be used for minimizing the Cramér-Rao bounds (CRBs). In contrast, this work proposes a unified approach that bridges the gap between max-FP and min-FP. Particularly, we examine the theoretical basis of this unified approach from a minorization-maximization (MM) perspective, and in return obtain a matrix extension of this new FP technique. Moreover, this work presents two application cases: (i) joint radar sensing and (ii) multi-cell secure transmission, neither of which can be efficiently addressed by the existing FP tools.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Client Selection Method Based on Loss Function Optimization for Federated Learning

引用

Computer Modeling in Engineering & sciences 2023年第10期137卷 1047-1064页

作者： Yan Zeng Siyuan Teng Tian Xiang Jilin Zhang Yuankai Mu Yongjian Ren Jian Wan School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Complex System Modeling and Simulation Ministry of EducationHangzhou310018China Zhejiang Engineering Research Center of Data Security Governance Hangzhou310018China Intelligent Robotics Research Center Zhejiang LabHangzhou311100China HDU-ITMO Joint Institute Hangzhou Dianzi UniversityHangzhou310018China

Federated learning is a distributedmachine learningmethod that can solve the increasingly serious problemof data islands and user data privacy,as it allows training data to be kept locally and not shared with other *** trains a globalmodel by aggregating locally-computedmodels of clients rather than their ***,the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global *** this problem,we focus on the client selection with federated learning,which can affect the convergence performance of the global model with the selected local *** propose FedChoice,a client selection method based on loss function optimization,to select appropriate local models to improve the convergence of the global *** firstly sets selected probability for clients with the value of loss function,and the client with high loss will be set higher selected probability,which can make them more likely to participate in ***,it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction,respectively,and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviationof the local gradient causedby *** experiments to verify the validity of FedChoice on CIFAR-10,CINIC-10,MNIST,EMNITS,and FEMNIST datasets,and the results show that the convergence of FedChoice is significantly improved,compared with FedAvg,FedProx,and FedNova.

关键词： Federated learning model aggregation Non-IID

来源：评论

学校读者我要写书评

暂无评论

Gradient and Variable Tracking with Multiple Local SGD for Decentralized Non-Convex Learning

arXiv

引用

arXiv 2023年

作者： Ge, Songyang Chang, Tsung-Hui The Shenzhen Research Institute of Big Data The School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China

Stochastic distributed optimization methods that solve an optimization problem over a multi-agent network have played an important role in a variety of large-scale signal processing and machine leaning applications. Among the existing methods, the gradient tracking (GT) method is found robust against the variance between agents’ local data distribution, in contrast to the distributed stochastic gradient descent (SGD) methods which have a slowed convergence speed when the agents have heterogeneous data distributions. However, the GT method can be communication expensive due to the need of a large number of iterations for convergence. In this paper, we intend to reduce the communication cost of the GT method by integrating it with the local SGD technique. Specifically, we propose a new local stochastic GT (LSGT) algorithm where, within each communication round, the agents perform multiple SGD updates locally. Theoretically, we build the convergence conditions of the _LSGT algorithm and show that it can have an improved convergence rate of O(1/√ET), where E is the number of local SGD updates and T is the number of communication rounds. We further extend the LSGT algorithm to solve a more complex learning problem which has linearly coupled variables inside the objective function. Experiment results demonstrate that the proposed algorithms have significantly improved convergence speed even under heterogeneous data distribution. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Block-gram: Mining Knowledgeable Features for Smart Contract Vulnerability Detection 7th

Block-gram: Mining Knowledgeable Features for Smart Contrac...

引用

7th International Conference on Smart computing and Communication, SmartCom 2022

作者： Li, Tao Wang, Haolong Fang, Yaozheng Jian, Zhaolong Wang, Zichun Xie, Xueshuo Tianjin Key Laboratory of Network and Data Security Technology Tianjin China College of Computer Science Nankai University Tianjin China Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province Hangzhou China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031281235

Effective vulnerability detection of large-scale smart contracts is critical because smart contract attacks frequently bring about tremendous economic loss. However, code analysis requiring traversal paths and learning methods requiring many features training is too time-consuming to detect large-scale on-chain contracts. This paper focuses on improving detection efficiency by reducing the dimension of the features, combined with expert knowledge. We propose a feature extraction method Block-gram to form low-dimensional knowledgeable features from the bytecode. We first separate the metadata and convert the runtime code to opcode sequence, dividing the opcode sequence into segments according to some instructions (jump, etc.). Then, we mine extensible Block-gram features for learning-based model training, consisting of 4-dimensional block features and 8-dimensional attribute features. We evaluate these knowledge-based features using seven state-of-the-art learning algorithms to show that the average detection latency speeds up 25 to 650 times, compared with the features extracted by N-gram. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization

arXiv

引用

arXiv 2023年

作者： Chen, Lesi Xu, Jing Luo, Luo School of Data Science Fudan University Shanghai China Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China

We consider the optimization problem of the form minx∈Rd f(x) EΞ[F(x;Ξ)], where the component F(x;Ξ) is L-mean-squared Lipschitz but possibly nonconvex and nonsmooth. The recently proposed gradient-free method requires at most O(L4d3/2ϵ-4 + ΔL3d3/2δ-1ϵ-4) stochastic zeroth-order oracle complexity to find a (δ, ϵ)- Goldstein stationary point of objective function, where Δ = f(x0) - infx∈Rd f(x) and x0 is the initial point of the algorithm. This paper proposes a more efficient algorithm using stochastic recursive gradient estimators, which improves the complexity to O(L3d3/2ϵ-3 + ΔL2d3/2δ-1ϵ-3). Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

JSRevealer: A Robust Malicious JavaScript Detector against Obfuscation

JSRevealer: A Robust Malicious JavaScript Detector against O...

引用

International Conference on Dependable Systems and Networks (DSN)

作者： Kunlun Ren Weizhong Qiang Yueming Wu Yi Zhou Deqing Zou Hai Jin 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 Huazhong University of Science and Technology Wuhan China Jinyinhu Laboratory Wuhan China Nanyang Technological University Singapore 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 Wuhan China

Due to the convenience and popularity of Web applications, they have become a prime target for attackers. As the main programming language for Web applications, many methods have been proposed for detecting malicious JavaScript, among which static analysis-based methods play an important role because of their high effectiveness and efficiency. However, obfuscation techniques are commonly used in JavaScript, which makes the features extracted by static analysis contain many useless and disguised features, leading to many false positives and false negatives in detection results. In this paper, we propose a novel method to find out the essential features related to the semantics of JavaScript code. Specifically, we develop JS-Revealer, a robust, effective, scalable, and interpretable detector for malicious JavaScript. To test the capabilities of JSRevealer, we conduct comparative experiments with four other state-of-the-art malicious JavaScript detection tools. The experimental results show that JSRevealer has an average F1 of 84.8% on the data obfuscated by different obfuscators, which is 21.6%, 22.3%, 18.7%, and 22.9% higher than the tools CUJO, ZOZZLE, JAST, and JSTAP, respectively. Moreover, the detection results of JSRevealer can be interpreted, which can provide meaningful insights for further security research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

Downstream-agnostic Adversarial Examples

引用

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：

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient Large Recommendation Model Training with Near CXL Memory Processing

Enabling Efficient Large Recommendation Model Training with ...

引用

Annual International Symposium on Computer Architecture, ISCA

作者： Haifeng Liu Long Zheng Yu Huang Jingyi Zhou Chaoqiang Liu Runze Wang Xiaofei Liaot Hai Jinf Jingling Xue 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 China School of Computer Science and Engineering University of New South Wales Australia Zhejiang Lab Hangzhou China

ISBN: (数字)9798350326581

ISBN: (纸本)9798350326598

Personalized recommendation systems have become one of the most important Internet services nowadays. A critical challenge of training and deploying the recommendation models is their high memory capacity and bandwidth demands, with the embedding layers occupying hundreds of GBs to TBs of storage. The advent of memory disaggregation technology and Compute Express Link (CXL) provides a promising solution for memory capacity scaling. However, relocating memory-intensive embedding layers to CXL memory incurs noticeable performance degradation due to its limited transmission bandwidth, which is significantly lower than the host memory bandwidth. To address this, we introduce ReCXL, a CXL memory disaggregation system that utilizes near-memory processing for scalable, efficient recommendation model training. ReCXL features a unified, hardwareefficient NMP architecture that processes the entire embedding training within CXL memory, minimizing data transfers over the bandwidth-limited CXL and enhancing internal bandwidth. To further improve the performance, ReCXL incorporates softwarehardware co-optimizations, including sophisticated dependencyfree prefetching and fine-grained update scheduling, to maximize hardware utilization. Evaluation results show that ReCXL outperforms the CPU-GPU baseline and the naïve CXL memory by $7.1 \times \sim 10.6 \times(9.4 \times$ on average) and $12.7 \times \sim 31.3 \times(22.6 \times$ on average), respectively.

关键词： Training Degradation Scalability Prefetching Memory management Web and internet services Bandwidth

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：