检索结果-内蒙古大学图书馆

The Journal of Machine Learning research 2023年第1期24卷 10845-10871页

作者： Zhengyu Zhou Weiwei Liu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

This paper investigates the sample complexity of learning a distributionally robust predictor under a particular distributional shift based on χ2-divergence, which is well known for its computational feasibility and statistical properties. We demonstrate that any hypothesis class ℌ with finite VC dimension is distributionally robustly learnable. Moreover, we show that when the perturbation size is smaller than a constant, finite VC dimension is also necessary for distributionally robust learning by deriving a lower bound of sample complexity in terms of VC dimension.

关键词： distributionally robustness PAC learning sample complexity χ2-divergence

来源：评论

学校读者我要写书评

暂无评论

Information-centric networking routing challenges and Bio/ACO-inspired solution: A review 9th

Information-centric networking routing challenges and Bio/AC...

引用

9th International Conference on Swarm Intelligence, ICSI 2018

作者： Zhang, Qingyi Wang, Xingwei Huang, Min Lv, Jianhui School of Computer Science and Engineering Northeastern University Shenyang China College of Software Northeastern University Shenyang China State Key Laboratory of Synthetical Automation for Process Industries School of Information Science and Engineering Northeastern University Shenyang China Central Research Institute Network Technology Laboratory Huawei Technologies Co. Ltd Shenzhen China

ISBN: (纸本)9783319938141

Information-Centric networking (ICN) aims to distribute and retrieve the content by name. In this paper, we review and approve the feasible Ant Colony Optimization (ACO)-inspired ICN routing solutions, i.e., applying ACO to solve ICN routing problem. At first, some significant challenges with respect to ICN routing are analyzed, such as explosive increasing of Forwarding Information Base (FIB), retrieval of closest content copy, uniform distribution of content and mobility support. Then, the solutions inspired by biology feature and behavior is reviewed. In addition, a general design thought of ACO-inspired solution is presented. Finally, the feasibility of ACO-inspired ICN routing solution is evaluated. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Ranking the Importance of Classes via software Structural Analysis

Ranking the Importance of Classes via Software Structural An...

引用

2011 International Conference on Future Communication, Computing, Control and Management(ICF4C 2011)

作者： Li Ding-wei Li Bing He Peng Pan Wei-feng State Key Laboratory of Software Engineering Wuhan University Complex Networks Research Center Wuhan University School of Computer Science and Information Engineering Zhejiang Gongshan University

How to identify important classes in an object-oriented system is a significant task for resources allocation and decision makingHowever, the work on ranking the importance of classes is scarceThis paper introduces a weighted software network model to represent the structure of object-oriented software, and based on which an indicator, IC, is defined to measure the importance of classesBy ranking the ICs of all classes we can obtain the important classes we should focus onManually inspection of the source code verifies the meaningfulness of the classes obtained and also validates the feasibility of our approach.

关键词： Importance of classes,software,software networks,complex networks

来源：评论

学校读者我要写书评

暂无评论

Coupled-view based ranking optimization for person re-identification 21

Coupled-view based ranking optimization for person re-identi...

引用

21st International Conference on MultiMedia Modeling, MMM 2015

作者： Ye, Mang Chen, Jun Leng, Qingming Liang, Chao Wang, Zheng Sun, Kaimin National Engineering Research Center for Multimedia Software School of Computer Wuhan University Wuhan430072 China Research Institute of Wuhan University in Shenzhen China School of Information Science and Technology Jiujiang University China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University China

ISBN: (纸本)9783319144443

Person re-identification aims to match different persons observed in non-overlapping camera views. researchers have proposed many person descriptors based on global or local descriptions, while both of them have achieved satisfying matching results, however, their ranking lists usually vary a lot for the same query person. These motivate us to investigate an approach to aggregate them to optimize the original matching results. In this paper, we proposed a coupled-view based ranking optimization method through cross KNN rank aggregation and graphbased re-ranking to revise the original ranking lists. Its core assumption is that the images of the same person should share the similar visual appearance in both global and local views. Extensive experiments on two datasets show the superiority of our proposed method with an average improvement of 20-30% over the state-of-the-art methods at CMC@1. © Springer International Publishing Switzerland 2015.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Fabricating PVDF hollow fiber microfiltration membrane with a tenon-connection structure via the thermally induced phase separation process to enhance strength and permeability

引用

European Polymer Journal 2019年 111卷 49-62页

作者： Cui, Zhenyu Li, Wei Zeng, Haiyi Tang, Xiuxiu Zhang, Jing Qin, Shuhao Han, Na Li, Jianxin State Key Laboratory of Separation Membranes and Membrane Processes/National Center for International Joint Research on Separation Membranes School of Material Science and Engineering Tianjin Polytechnic University Tianjin 300387 China School of Computer Science and Software Engineering Tianjin Polytechnic University Tianjin 300387 China National Engineering Research Canter for Compounding and Modification of Polymer Materials Guiyang 550014 China

In this work, thermally induced phase separation (TIPS) method was adopted to manufacture polyvinylidene fluoride (PVDF) blend hollow fiber microfiltration membrane with tenon-connection structure, which is used to fasten in Chinese traditional building by the stronger friction between rabbet and mortise, for water treatment by blending polyvinyl butyral (PVB). In this microstructure formation process, the distribution of PVB within the matrix and its regulatory role were investigated. Especially, the comprehensive effect of rabbeting and PVB adhesion on strength (The maximum breaking strength reached 17.08 MPa) was discussed. The results showed that a suitable PVB will markedly reduce the thickness of skin-layer close to the outside surface even for the solid-liquid (S-L) phase separation while the excessive PVB result in a thick skin-layer. Besides the strength, PVB markedly improved the hydrophilicity and permeability of the membrane. The breaking strength is more than 8 MPa, the maximum pure water flux is as high as 929.23 L m⁻² h⁻¹ and the rejection rate of carbon particles is nearly 100% even the polymer content is only 22%. In addition, the membrane showed a β-phase and an improved anti-fouling capacity. The investigation presented a simple way to regulate microstructure, enhance mechanical strength, flux and anti-fouling capacity of the membrane via the TIPS process for water treatment. © 2018

关键词： Adhesion effect Permeability Strengthening Tenon-connection Thermally induced phase separation

来源：评论

学校读者我要写书评

暂无评论

TraCemop: Towards Federated Learning with Traceable Contribution Evaluation and Model Ownership Protection

引用

IEEE Transactions on Mobile Computing 2025年

作者： Liu, Jingwei Zhou, Zihan Sun, Rong Liu, Lei Lu, Rongxing Dustdar, Schahram Niyato, Dusit Ministry of Education Engineering Research Center of Blockchain Technology Application and Evaluation China Xidian University Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an 710071 China Xidian University State Key Laboratory of Integrated Services Networks Xi'an 710071 China Xidian University Guangzhou Institute of Technology Guangzhou 510555 China Qilu University of Technology (Shandong Academy of Sciences) Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan 250014 China Queen's University School of Computing Kingston K7L 2N8 ON Canada TU Wien Distributed Systems Group Austria UPF ICREA Barcelona Spain Nanyang Technological University School of Computer Science and Engineering Singapore

Federated Learning (FL) allows multiple clients to collaboratively train machine learning models without the need to share their local private data. As a result, it can effectively address the issue of data fragmentation. Nevertheless, insufficient evaluation of individual contributions and the lack of protections for both the intellectual property rights (IPR) of models and client privacy can greatly reduce clients' motivations in federated training. To address these challenges, this paper introduces the Traceable Contribution Evaluation and Model Ownership Protection (TraCemop) framework for federated learning, which allows each client to swiftly assess the contributions of others in each round, with integrated support for the traceability of evaluation results. To safeguard the intellectual property of models, a collective watermark is embedded in the global model. Additionally, a secure mechanism for verifying model ownership is also available in case of disputes. Security analysis indicates that TraCemop is capable of resisting data reconstruction attacks as well as various types of model copyright infringements. Finally, we evaluate the proposed framework using two commonly-used datasets, and the experimental results show a significant improvement in the efficiency of contribution evaluation compared to existing methods. Meanwhile, IPR infringement tests on TraCemop reveal that the proposed framework is resilient against malicious efforts to monopolize model ownership. © 2002-2012 IEEE.

关键词： Blockchain Contribution evaluation Federated learning Model IPR Watermark

来源：评论

学校读者我要写书评

暂无评论

Flush+Time: A High Accuracy and High Resolution Cache Attack On ARM-FPGA Embedded SoC 38

Flush+Time: A High Accuracy and High Resolution Cache Attack...

引用

38th IEEE VLSI Test Symposium, VTS 2020

作者： Tang, Churan Liu, Pengkun Ma, Cunqing Liu, Zongbin Ge, Jingquan State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Intelligent Software Research Center Institute of Software CAS Beijing China School of Computer and Science University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728153599

Flush based cache attacks have become a practical threat to data privacy and information security due to their advantages such as high accuracy and resolution. However, their accuracy and resolution still has room for improvement. In addition, although most of the attacks have been demonstrated on x86 processors, few of them have been executed on ARM devices. We propose a high accuracy, high resolution flush based cache attack, Flush+Time. This technique solves two important challenges for cache attacks on ARM: how to flush cache lines and how to achieve precise timing. Experiments show that Flush+Time increases accuracy from 95.1% of Flush+Reload, the most powerful general cache attack so far, to 99.3%. Flush+Time has a 30.5% higher resolution than Flush+Reload, but its execution time is only 0.59 times that of Spectre. © 2020 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Person re-identification using data-driven metric adaptation 21

Person re-identification using data-driven metric adaptation

引用

21st International Conference on MultiMedia Modeling, MMM 2015

作者： Wang, Zheng Hu, Ruimin Liang, Chao Jiang, Junjun Sun, Kaimin Leng, Qingming Huang, Bingyue National Engineering Research Center for Multimedia Software School of Computer Wuhan University Wuhan China Research Institute of Wuhan University in Shenzhen China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China School of Information Science & Technology Jiujiang University Jiujiang China

ISBN: (纸本)9783319144412

Person re-identification, aiming to identify images of the same person from various cameras configured in difference places, has attracted plenty of attention in the multimedia community. In person re-identification procedure, choosing a proper distance metric is a crucial aspect [2]. Traditional methods always utilize a uniform learned metric, which ignored specific constraints given by this re-identification task that the learned metric is highly prone to over-fitting [21], and each person holding their unique characteristic brings inconsistency. Therefore, it is obviously inappropriate to merely employ a uniform metric. In this paper, we propose a data-driven metric adaptation method to improve the uniform metric. The key novelty of the approach is that we re-exploits the training data with cross-view consistency to adaptively adjust the metric. Experiments conducted on two standard data sets have validated the effectiveness of the proposed method with a significant improvement over baseline methods. © Springer International Publishing Switzerland 2015.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Region-based interactive ranking optimization for person re-identification 15

Region-based interactive ranking optimization for person re-...

引用

15th Pacific-Rim Conference on Multimedia, PCM 2014

作者： Wang, Zheng Hu, Ruimin Liang, Chao Leng, Qingming Sun, Kaimin National Engineering Research Center for Multimedia Software School of Computer Wuhan University Wuhan China Research Institute of Wuhan University in Shenzhen China School of Information Science and Technology Jiujiang University Jiujiang China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China

ISBN: (纸本)9783319131672

Person re-identification, aiming to identify images of the same person from various cameras configured in difference places, has attracted plenty of attention in the multimedia community. Previous work mainly focuses on feature presentation and distance measure, and achieves promising results on some standard databases. However, the performance is still not good enough due to appearance changes caused by variations in illuminations, poses, viewpoints and occlusion. This paper addresses the problem through result re-ranking by introducing user feedback. In particular, considering the peculiarity of scarce positive and global similar negative samples in the person re-identification problem, we propose a region-based interactive ranking optimization method, to improve the original query result by labeling locally similar and dissimilar image regions. Experiments conducted on two standard data sets have validated the effectiveness of the proposed method with an average improvement of 10-30% over original basic method. It is proved that the ranking optimization algorithm is both an effective and efficient method to improve the original person re-identification result. © Springer International Publishing Switzerland 2014.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

A fibonacci based batch auditing protocol for cloud data 1

引用

9th International Symposium on Cyberspace Safety and Security, CSS 2017

作者： Shen, Jian Shen, Jun Wang, Chen Wang, Anxi Jiangsu Engineering Center of Network Monitoring Nanjing China Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology Nanjing China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China

ISBN: (数字)9783319694719

ISBN: (纸本)9783319694702

As cloud storage is developing fast with time going by, the design of auditing protocols has caught a large number of researchers’ eyes. However, though most of the existing auditing protocols have considered batch auditing to save resources in the auditor side, the design of methods to locate the specific positions of the corrupted data blocks is ignored. In this paper, we propose a novel batch auditing protocol based on the Fibonacci sequence to save resources in the cloud, which is an extension of our previous work. Experimental results and numerical analysis indicate that the proposed scheme is efficient. © 2017, Springer International Publishing AG.

关键词： Cloud storage

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：