检索结果-南通市图书馆

Privacy Distributed Constrained Optimization Over Time-Varying Unbalanced Networks and Its Application in Federated Learning

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 335-346页

作者： Mengli Wei Wenwu Yu Duxin Chen Mingyu Kang Guang Cheng the school of Cyber Science and Engineering Southeast University IEEE the school of mathematics Frontiers Science Center for Mobile Information Communication and Security Southeast University the Purple Mountain Laboratories the school of mathematics Southeast University

This paper investigates a class of constrained distributed zeroth-order optimization(ZOO) problems over timevarying unbalanced graphs while ensuring privacy preservation among individual agents. Not taking into account recent progress and addressing these concerns separately, there remains a lack of solutions offering theoretical guarantees for both privacy protection and constrained ZOO over time-varying unbalanced *** hereby propose a novel algorithm, termed the differential privacy(DP) distributed push-sum based zeroth-order constrained optimization algorithm(DP-ZOCOA). Operating over time-varying unbalanced graphs, DP-ZOCOA obviates the need for supplemental suboptimization problem computations, thereby reducing overhead in comparison to distributed primary-dual methods. DP-ZOCOA is specifically tailored to tackle constrained ZOO problems over time-varying unbalanced graphs,offering a guarantee of convergence to the optimal solution while robustly preserving privacy. Moreover, we provide rigorous proofs of convergence and privacy for DP-ZOCOA, underscoring its efficacy in attaining optimal convergence without constraints. To enhance its applicability, we incorporate DP-ZOCOA into the federated learning framework and formulate a decentralized zeroth-order constrained federated learning algorithm(ZOCOA-FL) to address challenges stemming from the timevarying imbalance of communication topology. Finally, the performance and effectiveness of the proposed algorithms are thoroughly evaluated through simulations on distributed least squares(DLS) and decentralized federated learning(DFL) tasks.

关键词： Constrained distributed optimization decentralized federated learning (DFL) differential privacy (DP) time-varying unbalanced graphs zeroth-order gradient

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Aperiodically semi-intermittent-based fixed-time stabilization and synchronization of delayed discontinuous inertial neural networks

引用

Science China(information Sciences) 2025年第1期68卷 238-254页

作者： Guodong ZHANG Jinde CAO school of mathematics and Statistics South-Central Minzu University school of mathematics Southeast University

This article concentrates on the fixed-time stabilization(FS) and fixed-time synchronization(FTS) of discontinuous inertial neural networks(DINNs) with distributed delays. Using mathematical induction to a new differential equality, a novel fixed-time stability lemma is constructed. Then, by designing an aperiodically semi-intermittent switching control and combining it with the theory of nonsmooth analysis, some novel criteria on the FS and FTS of DINNs are obtained. Unlike the methods used in most existing studies, the FS and FTS results are structured using the newly proposed fixed-time stability lemma and the nonreduced-order approach, resulting in broader practical applications and strengthening the scientific quality of the derived results. Lastly, numerical simulations and applications proffer the effectiveness of the established FS and FTS criteria.

关键词： inertial neural networks fixed-time synchronization semi-intermittent switching control nonreduced-order approach fixed-time stabilization

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

New results on finite-time stability and instability theorems for stochastic nonlinear time-varying systems

引用

Science China(information Sciences) 2025年第2期68卷 186-199页

作者： Weihai ZHANG Liqiang YAO College of Electrical Engineering and Automation Shandong University of Science and Technology school of mathematics and information Science Yantai University

This paper studies finite-time stability and instability theorems in the probability sense for stochastic nonlinear timevarying systems. Firstly, a new sufficient condition is proposed to guarantee that the considered system has a global ***, we propose new finite-time stability and instability criteria that relax the constraints on LV(the infinitesimal operator of Lyapunov function V) by the uniformly asymptotically stable function. On the one hand, these obtained results make up for the shortcomings of the existing results. On the other hand, the new finite-time stability theorems can be viewed as natural extensions of the existing results and also allow LV to be indefinite(negative or positive) rather than just only allow LV < ***, some simulation examples verify the validity of the theoretical results.

关键词： stochastic nonlinear systems finite-time stability finite-timeinstability uniformly asymptotically stable function

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Unsupervised multiplex graph diffusion networks with multi-level canonical correlation analysis for multiplex graph representation learning

引用

Science China(information Sciences) 2025年第03期68卷 66-79页

作者： Sichao FU Qinmu PENG Yange HE Baokun DU Bin ZOU Xiao-Yuan JING Xinge YOU school of Electronic information and Communications Huazhong University of Science and Technology Platform Operation and Marketing Center JD Retail Faculty of mathematics and Statistics Hubei Key Laboratory of Applied Mathematics Hubei University school of Computer Science Wuhan University

In recent years, unsupervised multiplex graph representation learning(UMGRL) has received increasing research interest, which aims to learn discriminative node features from the multiplex graphs supervised by data without the guidance of labels. Although these designed UMGRL methods have obtained great success in various graph-related tasks, most existing UMGRL models still have the following issues: highly depending on complex self-supervised strategies(i.e., data augmentation,pretext tasks, and negative pairs sampling), restricted receptive fields, and only aggregating low-frequency information between nodes. In this paper, we propose a simple unsupervised multiplex graph diffusion network(UMGDN) with the aid of multi-level canonical correlation analysis to solve the above issues. Specifically, we first decouple the feature transform and propagation processes of the graph convolution layer to further improve the generalization of the learnable parameters. And then, we propose adaptive diffusion propagation to capture long-range dependency relationships between nodes, not the local neighborhood interactions. Finally, a multi-level canonical correlation analysis loss on both the feature transform and propagation processes is proposed to maximize the correlation of the same node features from multiple graphs for guiding model optimization. Compared to the existing UMGRL models, our proposed UMGDN does not need to introduce any data augmentation, negative pairs sampling techniques, complex pretext tasks, and also adaptively aggregates the optimal frequency information between nodes to generate more robust node embeddings. Extensive experiments on four popular datasets and two graph-related tasks demonstrate the effectiveness of the proposed method.

关键词： unsupervised multiplex graph representation learning graph neural networks node classification node clustering

来源：

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Bifurcations and Spatiotemporal Patterns in the Diffusive Nutrient-Microor ganism Model

引用

Acta Mathematicae Applicatae Sinica 2025年第1期41卷 162-178页

作者： Ya-di WANG Hai-long YUAN Yan-ling LI school of Arts and Sciences Shaanxi University of Science and TechnologyXi'an 710021China school of mathematics and Statistics Xi'an Jiaotong UniversityXi'an 710049China school of mathematics and information Science Shaanxi Normal UniversityXi'an 710062China

In this paper,the diffusive nutrient-microorganism model subject to Neumann boundary conditions is *** Hopf bifurcations and steady state bifurcations which bifurcate from the positive constant equilibrium of the system are investigated in *** addition,the formulae to determine the direction of Hopf and steady state bifurcations are *** results show the existence of spatially homogeneous/nonhomogeneous periodic orbits and steady state solutions,which indicates the spatiotemporal dynamics of the *** numerical simulations are also presented to support the analytical results.

关键词： nutrient-microorganism model Hopf bifurcation steady state bifurcation simulations

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

Science China(information Sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN school of information and Communication Technology Griffith University school of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of mathematics and Computer Science University of Bremen Faculty of information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology school of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Federated local causal structure learning

引用

Science China(information Sciences) 2025年第03期68卷 110-124页

作者： Kui YU Chen RONG Hao WANG Fuyuan CAO Jiye LIANG school of Computer and information Hefei University of Technology school of Computer and information Technology Shanxi University

Local causal structure learning(LCS) efficiently identifies a set of direct neighbors of a specified variable from observational data. Additionally, it distinguishes direct causes and direct effects of this variable without learning the entire causal structure. While many LCS algorithms have been proposed, they do not consider the data privacy-preserving problem,which has attracted extensive attention from academia and industry. To address this issue, we propose a federated local causal structure learning(FedLCS) algorithm to learn local causal structures in privacy-preserving data in a federated ***, FedLCS introduces a layer-wise federated local skeleton learning algorithm to construct the local skeleton. Based on this skeleton, it introduces a federated local skeleton orientation algorithm and an extension-and-backtracking orientation algorithm to orient the edges. Finally, FedLCS uses a federated local extension-and-backtracking orientation algorithm to orient the remaining edges. Extensive experiments on benchmark, synthetic, and real datasets demonstrate that FedLCS can learn the local causal structure of a given variable in a federated setting.

关键词： local causal structure learning federated learning directed acyclic graph privacy-preserving data federated layer-wise strategy

来源：

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Self-Triggered Impulsive Control for Nonlinear Stochastic Systems

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 264-266页

作者： Tao Zhan Yi Ji Yabin Gao Hongyi Li Yuanqing Xia the school of mathematics and Statistics Southwest University the school of Astronautics Harbin Institute of Technology IEEE the College of Electronic and information Engineering Southwest University Zhongyuan university of Technology the school of Automation Beijing Institute of Technology

Dear Editor,This letter deals with the stabilization problem of nonlinear stochastic systems via self-triggered impulsive control(STIC), where the timing of impulsive control actions is not dependent on continuous state monitoring. In contrast to the existing self-triggered control method, novel self-triggered mechanism(STM) is proposed by incorporating a waiting time for stabilizing impulses. This allows for direct prediction of the next impulsive instant.

关键词： Stabilization

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Stabilities of delay stochastic McKean-Vlasov equations in the G-framework

引用

Science China(information Sciences) 2025年第1期68卷 255-277页

作者： Haiyan YUAN Quanxin ZHU Department of mathematics Heilongjiang Institute of Technology Key Laboratory of Computing and Stochastic mathematics (Ministry of Education) School of Mathematics and Statistics Hunan Normal University

This article focuses on a type of stochastic Mc Kean-Vlasov equation in the G-framework(G-SMVE) and addresses the stability issue for delay stochastic Mc Kean-Vlasov equations in the G-framework(G-SMVDEs). Distribution dependence and uncertainty prevent us from directly applying the stochastic analysis method for stochastic Mc Kean-Vlasov equations(SMVEs)to G-SMVEs directly. To overcome this difficulty, we introduce definitions, including the derivative of a function with a law under the G-expectation and the Lions derivatives. Then we construct a new G-It? formula for G-SMVEs according to the G-It? formula for stochastic differential equations in the G-framework(G-SDEs) and the It? formula for SMVEs. Using the new G-It? formula and the Lyapunov functional method, we investigate the moment exponential stability and almost sure asymptotic stability of G-SMVDEs. To overcome the difficulty in obtaining the distribution dependence of the exact solution to the G-SMVDE, we introduce the empirical measure and the corresponding interacting particle system, and then prove the stability equivalence between the underlying G-SMVDE and the corresponding interacting particle system. Two examples are used to confirm our theoretical results.

关键词： delay stochastic McKean-Vlasov equations Wasserstein distance G-Brownian motion Lions derivative stability

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Graph reinforcement learning with relational priors for predictive power allocation

引用

Science China(information Sciences) 2025年第2期68卷 230-247页

作者： Jianyu ZHAO Chenyang YANG school of Electronics and information Engineering Beihang University

Deep reinforcement learning for resource allocation has been investigated extensively owing to its ability of handling model-free and end-to-end problems. However, its slow convergence and high time complexity during online training hinder its practical use in dynamic wireless systems. To reduce the training complexity, we resort to graph reinforcement learning for leveraging two kinds of relational priors inherent in many wireless communication problems: topology information and permutation properties. To harness the two priors, we first conceive a method to convert the state matrix into a state graph,and then propose a graph deep deterministic policy gradient(DDPG) algorithm with the desired permutation property. To demonstrate how to apply the proposed methods, we consider a representative problem of using reinforcement learning, predictive power allocation, which minimizes the energy consumption while ensuring the quality-of-service of each user requesting video streaming. We derive the time complexity required by training the proposed graph DDPG algorithm and fully-connected neural network-based DDPG algorithm in each time step. Simulations show that the graph DDPG algorithm converges much faster and needs much lower time and space complexity than existing DDPG algorithms to achieve the same learning performance.

关键词： reinforcement learning graph neural network relational priors resource allocation

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：