检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Dejun Ye, Kai Zheng, Zimo Zhou, Tao Yen, Gary G. Jiang, Min Department of Artificial Intelligence School of Informatics Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen361005 China School of Electrical and Computer Engineering Oklahoma State University StillwaterOK74075 United States

Bilevel optimization problems are characterized by an interactive hierarchical structure, where the upper level seeks to optimize its strategy while simultaneously considering the response of the lower level. Evolutionary algorithms are commonly used to solve complex bilevel problems in practical scenarios, but they face significant resource consumption challenges due to the nested structure imposed by the implicit lower-level optimality condition. This challenge becomes even more pronounced as problem dimensions increase. Although recent methods have enhanced bilevel convergence through task-level knowledge sharing, further efficiency improvements are still hindered by redundant lower-level iterations that consume excessive resources while generating unpromising solutions. To overcome this challenge, this paper proposes an efficient dynamic resource allocation framework for evolutionary bilevel optimization, named DRCBLEA. Compared to existing approaches, DRC-BLEA introduces a novel competitive quasi-parallel paradigm, in which multiple lower-level optimization tasks, derived from different upperlevel individuals, compete for resources. A continuously updated selection probability is used to prioritize execution opportunities to promising tasks. Additionally, a cooperation mechanism is integrated within the competitive framework to further enhance efficiency and prevent premature convergence. Experimental results compared with chosen state-of-the-art algorithms demonstrate the effectiveness of the proposed method. Specifically, DRCBLEA achieves competitive accuracy across diverse problem sets and real-world scenarios, while significantly reducing the number of function evaluations and overall running time. © 2024, CC BY-NC-ND.

关键词： Structural optimization

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'an710071 China Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China Xidian University Guangzhou Institute of Technology Guangzhou510555 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250014 China Queen's University School of Computing KingstonONK7L 2N8 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： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Reservoir Operation Management Considering the Influence of Inter-Basin Water Transfer Project on Inflow 8th

Adaptive Reservoir Operation Management Considering the Infl...

引用

8th International Conference on Water Resource and Environment, WRE 2022

作者： Zhang, Xiaoqi Yang, Yuan Wang, Yongqiang Li, Yinghai Changjiang River Scientific Research Institute Changjiang Water Resources Commission of the Ministry of Water Resources of China Wuhan430010 China Hubei Key Laboratory of Water Resources and Eco-Environmental Sciences Changjiang River Scientific Research Institute Wuhan430010 China Research Center on the Yangtze River Economic Belt Protection and Development Strategy Hubei Wuhan430010 China College of Hydraulic and Environmental Engineering China Three Gorges University Yichang443002 China Engineering Research Center of Eco-Environment in Three Gorges Reservoir Region Ministry of Education China Three Gorges University Yichang443002 China

ISBN: (纸本)9789819919185

The seasonal flood limited water level (FLWL) is one of the important ways for the reservoir to efficiently use flood resources under the premise of meeting flood control requirements in the flood season. This paper established the joint distribution of summer and autumn maximum 7-day flood volume based on the Copula theory by considering the impact of inter-basin water transfer projects, and then deduced the most probable combination form for seasonal floods with the help of the Lagrangian multiplier method. Finally, the optimal design of the seasonal FLWL scheme was obtained by building an optimal model with the objective function of maximizing the available water supply, where the joint distribution probability value was regarded as the main flood control constraint. Selecting China’s Danjiangkou Reservoir as a case study, the results show that: (1) The general form of the most likely combination of seasonal floods considering the impact of inter-basin water transfer projects is derived. (2) The optimal reservoir FLWLs in summer and autumn seasons are, respectively, 161.9 and 164.8 m. (3) The relative increment of the annual average diversion volume has increased by 1.8%, and the assurance probability of downstream water has increased by 0.79%, indicating that the optimized FLWLs have significantly improved the water supply. These research results are helpful to improve the flood resource utilization rate of the reservoir in the flood season. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Water supply

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Nestin prevents mesenchymal stromal cells from apoptosis in LPS-induced lung injury via inhibition of unfolded protein response sensor IRE1?

引用

Life Medicine 2022年第3期1卷 359-371页

作者： Hongmiao Wang Chenhao Jiang Jianye Cai Qiying Lu Yuan Qiu Yi Wang Yinong Huang Yong Xiao Boyan Wang Xiaoyue Wei Jiahao Shi Xingqiang Lai Tao Wang Jiancheng Wang Andy Peng Xiang Centre for Stem Cell Biology and Tissue Engineering Key Laboratory for Stem Cells and Tissue Engineering Ministry of Education Sun Yat-sen University Guangzhou 510080 China Department of Hepatic Surgery and Liver Transplantation Centre The Third Affiliated Hospital Sun Yat-sen University Guangzhou 510630 China Guangdong Key Laboratory of Liver Disease Research Guangdong Engineering Laboratory for Transplantation The Third Affiliated Hospital Sun Yat-sen University Guangzhou 510630 China Guangdong Institute for Drug Control NMPA Key Laboratory for Quality Control of Blood Products Guangdong Drug Administration Key Laboratory of Quality Control and Research of Blood Products Guangzhou 510663 China Department of Endocrinology The First Affiliated Hospital of Sun Yat-Sen University Guangzhou 510080 China Centre for Stem Cell Biology and Tissue Engineering Key Laboratory for Stem Cells and Tissue Engineering Ministry of Education Sun Yat-sen University Guangzhou 510080 China Scientific Research Centre The Seventh Affiliated Hospital Sun Yat-sen University Shenzhen 518107 China

The clinical applications of MSC therapy have been intensely investigated in acute respiratory distress syndrome. However, clinical studies have fallen short of expectations despite encouraging preclinical results. One of the key problems is that transplanted stem cells can hardly survive in the harsh inflammatory environment. Prolonging the survival of transplanted MSCs might be a promising strategy to enhance the therapeutic efficacy of MSC therapy. Here, we identified Nestin, a class VI intermediate filament, as a positive regulator of MSC survival in the inflammatory microenvironment. We showed that Nestin knockout led to a significant increase of MSC apoptosis, which hampered the therapeutic effects in an LPS-induced lung injury model. Mechanistically, Nestin knockout induced a significant elevation of endoplasmic reticulum (ER) stress level. Further investigations showed that Nestin could bind to IRE1? and inhibit ER stress-induced apoptosis under stress. Furthermore, pretreatment with IRE1? inhibitor 4?8C improved MSC survival and improved therapeutic effect. Our data suggests that Nestin enhances stem cell survival after transplantation by inhibiting ER stress-induced apoptosis, improving protection, and repair of the lung inflammatory injury.

关键词： acute respiratory distress syndrome LPS-induced lung injury ER stress IRE1? Nestin

来源：评论

学校读者我要写书评

暂无评论

Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis

arXiv

引用

arXiv 2022年

作者： Shi, Wenxuan Li, Fei Li, Jingye Fei, Hao Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China

The state-of-the-art model for structured sentiment analysis casts the task as a dependency parsing problem, which has some limitations: (1) The label proportions for span prediction and span relation prediction are imbalanced. (2) The span lengths of sentiment tuple components may be very large in this task, which will further exacerbates the imbalance problem. (3) Two nodes in a dependency graph cannot have multiple arcs, therefore some overlapped sentiment tuples cannot be recognized. In this work, we propose nichetargeting solutions for these issues. First, we introduce a novel labeling strategy, which contains two sets of token pair labels, namely essential label set and whole label set. The essential label set consists of the basic labels for this task, which are relatively balanced and applied in the prediction layer. The whole label set includes rich labels to help our model capture various token relations, which are applied in the hidden layer to softly influence our model. Moreover, we also propose an effective model to well collaborate with our labeling strategy, which is equipped with the graph attention networks to iteratively refine token representations, and the adaptive multi-label classifier to dynamically predict multiple relations between token pairs. We perform extensive experiments on 5 benchmark datasets in four languages. Experimental results show that our model outperforms previous SOTA models by a large margin. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Network Embedding with Topology-Aware Textual Representations 18th

Network Embedding with Topology-Aware Textual Representation...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Chen, Jiaxing Xu, Zenan Su, Qinliang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9783030891879

Textual network embedding aims to learn meaningful low-dimensional representations for vertices with the consideration of the associated texts. When learning the representations for texts in network embedding, existing methods mostly only exploit information from neighboring texts (i.e., contexts), while rarely taking advantages of the valuable network topological (structural) information. To bridge the gap, in this paper, a model based on adaptive-filter convolutional neural networks (CNN) is developed, in which the filters are adapted to local network topologies, rather than clamped to fixed values as in traditional CNNs. The dependency enables the learned text representations to be aware of local network topologies. It is shown that the proposed topology-aware representations can be viewed as a complement to existing context-aware ones. When the two are used together, experimental results on three real-world benchmarks demonstrate that significant performance improvements on the tasks of link prediction and vertex classification. © 2021, Springer Nature Switzerland AG.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Assisted Computation Offloading Collaboration: A Hierarchical Game to Fortify IoT Security and Resilience

SSRN

引用

SSRN 2023年

作者： Zhou, Zitao Ye, Fang Li, Yingsong Geng, Xiaoyu Zhang, Sitong Key Laboratory of Advanced Marine Communication and Information Technology College of Information and Communication Engineering Harbin Engineering University Harbin China National Key Laboratory of Underwater Acoustic Technology College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education College of Electronic and Information Engineering Anhui University Hefei China

With the rapid development of the Internet of Things (IoT), computation offloading collaboration has become an important solution to address the data processing challenges faced by resource-constrained devices. However, security and privacy issues have become a major concern in the computation offloading collaboration process. This paper proposes a blockchain-assisted computation offloading collaboration scheme, Blockchain-Assisted Computation Offloading Collaboration (BACOC). The scheme uses blockchain technology to assist computation offloading collaboration under IoT conditions to fortify security and resilience during the computation offloading process. At the same time, a hierarchical game model based on Stackelberg game theory and contract theory is adopted to determine the optimal service pricing strategy. Experimental and simulation results demonstrate the effectiveness and feasibility of the BACOC scheme. © 2023, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Adaptive ELM-Based Time-Constrained Control of Uncertain Robotic Manipulators With Minimum Learning Computation

引用

IEEE Transactions on Emerging Topics in computing 2025年

作者： Jin, Xiaozheng Hou, Yuhan Wu, Xiaoming Chi, Jing Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Shandong Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Jinan250013 China Qilu Institute of Technology School of Intelligent Manufacturing and Control Engineering Shandong Jinan250200 China Shandong University of Finance and Economics School of Computing and Artificial Intelligence Shandong Jinan250014 China

This paper studies the extreme learning machine (ELM)-based time-constrained trajectory tracking control of a class of robotic manipulator systems with model/input uncertainties, matched and mismatched disturbances. A uniform robust exact differentiator (URED) is developed to construct a multi-layer virtual control framework of the robotic manipulator system. Under the control framework, adaptive ELM-based control strategies are proposed to suppress the influence of the uncertainties and disturbances layer-by-layer, combining with the minimum learning parameter (MLP) technique which is employed to reduce the calculation complexity of ELM parameters. The significance of this study is that general model/input uncertainties, matched and mismatched disturbances can be effectively compensated within a limited time, so that bounded trajectory tracking of the robotic manipulator can be achieved avoiding the complexity explosion issue. The time-constrained stability of the closed-loop robotic error systems is proved through Lyapunov stability theory. Finally, comparative simulations are employed to display the feasibility and superiority of the designed robust adaptive ELM-based control schemes of a robotic manipulator system. © 2013 IEEE.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

SML: A Backdoor Defense for Non-Intrusive Speech Quality Assessment via Semi-Supervised and Multi-Task Learning

SML: A Backdoor Defense for Non-Intrusive Speech Quality Ass...

引用

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

作者： Ying Ren Wenjie Zhang Jiahong Ye Jie Li Diqun Yan Bin Ma Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China College of Digital Technology and Engineering Ningbo University of Finance and Economics Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Non-intrusive speech quality assessment (NISQA) is widely used in speech downstream tasks due to its ability to predict the quality of speech without a reference speech. However, few researchers have focused on the backdoor security of NISQA. Despite the backdoor defenses have been extensively studied to mitigate the threat of maliciously modifications in deep neural networks. In particular, semi-supervised based backdoor defenses have excellent defensive performance by depriving backdoor attacks of their most essential need. But these defense methods rely on data-augmentation consistency and thus cannot be applied to NISQA. In this work, we propose a backdoor defense based on semi-supervised and multi-task learning (SML). Semi-supervised learning is based on the simple assumption that the same input should be as consistent as possible in two similar models. Multi-task learning further improves the prediction performance of mean opinion score (MOS) by learning the tasks of perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI) and speech distortion index (SDI). Extensive experiments involving five backdoor defenses against five backdoor attacks on two benchmark datasets demonstrate the superiority of our SML approach.

关键词： Acoustic distortion Artificial neural networks Semisupervised learning Benchmark testing Multitasking Acoustics Quality assessment Security Indexes Speech processing

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：