检索结果-内蒙古大学图书馆

distributed Online Learning Over Multitask Networks With Rank-One Model

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS 2025年 11卷 314-328页

作者： Chen, Yitong Jin, Danqi Chen, Jie Richard, Cedric Zhang, Wen Huang, Gongping Chen, Jingdong Northwestern Polytech Univ Ctr Intelligent Acoust & Immers Commun Sch Marine Sci & Technol Xian 710072 Peoples R China Wuhan Univ Sch Elect Informat Wuhan 430072 Peoples R China Univ Cote Azur OCA CNRS F-06000 Nice France

Modeling multitask relations in distributed networks has garnered considerable interest in recent years. In this paper, we present a novel rank-one model, where all the optimal vectors to be estimated are scaled versions of an unknown vector to be determined. By considering the rank-one relation, we develop a constrained centralized optimization problem, and after a decoupling process, it is solved in a distributed way by using the projected gradient descent method. To perform an efficient calculation of this projection, we suggest substituting the intensive singular value decomposition with the computationally efficient power method. Additionally, local estimates targeting the same optimal vector are combined within a neighborhood to further improve their accuracy. Theoretical analyses of the proposed algorithm are conducted for star topologies, and conditions are derived to guarantee its stability in both the mean and mean-square senses. Finally, simulation results are presented to demonstrate the effectiveness of the proposed algorithms.

关键词： Vectors Topology Stars Network topology Supervised learning Principal component analysis distributed databases Training Location awareness Information processing Combination matrix distributed optimization multitask diffusion strategy power method rank-one model

来源：评论

学校读者我要写书评

暂无评论

Interventional Causal Structure Discovery Over Graphical Models With Convergence and Optimality Guarantees

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第1期12卷 156-172页

作者： Qiu, Chengbo Yang, Kai Tongji Univ Dept Comp Sci & Technol Shanghai 201800 Peoples R China

Learning causal structure from sampled data is a fundamental problem with applications in various fields, including healthcare, machine learning and artificial intelligence. Traditional methods predominantly rely on observational data, but there exist limits regarding the identifiability of causal structures with only observational data. Interventional data, on the other hand, helps establish a cause-and-effect relationship by breaking the influence of confounding variables. It remains to date under-explored to develop a mathematical framework that seamlessly integrates both observational and interventional data in causal structure learning. Furthermore, existing studies often focus on centralized approaches, necessitating the transfer of entire datasets to a single server, which lead to considerable communication overhead and heightened risks to privacy. To tackle these challenges, we develop a bilevel polynomial optimization (Bloom) framework. Bloom not only provides a powerful mathematical modeling framework, underpinned by theoretical support, for causal structure discovery from both interventional and observational data, but also aspires to an efficient causal discovery algorithm with convergence and optimality guarantees. We further extend Bloom to a distributed setting to reduce the communication overhead and mitigate data privacy risks. It is seen through experiments on both synthetic and real-world datasets that Bloom markedly surpasses other leading learning algorithms.

关键词： Optimization Polynomials Convergence Privacy distributed databases Data privacy Data models Symbols Noise Graphical models Bilevel optimization causal structure learning directed acyclic graph distributed setting graphical model interventional data polynomial optimization

来源：评论

学校读者我要写书评

暂无评论

DP-FedCMRS: Privacy-Preserving Federated Learning Algorithm to Solve Heterogeneous Data

引用

IEEE ACCESS 2025年 13卷 41984-41993页

作者： Zhang, Yang Long, Shigong Liu, Guangyuan Zhang, Junming Guizhou Univ State Key Lab Publ Big Data Guiyang 550025 Peoples R China Guizhou Univ Sch Comp Sci & Technol Guiyang 550025 Peoples R China Guizhou Polytech Construct Guiyang 551400 Peoples R China

In federated learning, non-independently and non-identically distributed heterogeneous data on the clients can limit both the convergence speed and model utility of federated learning, and gradients can be used to infer original data, posing a threat to user privacy. To address these issues, this paper proposes a Differential Privacy based Federated Learning algorithm with clustered model random selection (DPFedCMRS), which first clusters clients with similar data distributions into the same cluster, and then each cluster randomly selects a model from other clusters in iteration to learn the characteristics of different data distributions to solve the problem of data heterogeneity. Differential privacy is applied to the algorithm to achieve sample-level differential privacy and protect the client's data privacy. An adaptive clustering algorithm is also proposed, which combines gradient quantile sparsification to amplify data characteristics to Ensure high-accuracy clustering results under the condition of high privacy guarantee. Many experiments are carried out on three classical datasets, MNIST, FMNIST and CIFAR10, the accuracy of the model trained by DPFedCMRS is increased by 5.98%, 5.16% and 2.05% compared with the existing methods when the privacy budget is 2, indicating that DPFedCMRS improves the performance of federated learning in the case of highly heterogeneous data distribution and high privacy guarantee.

关键词： Federated learning Training distributed databases Data models Clustering algorithms Differential privacy Servers Privacy Adaptation models Computational modeling differential privacy non-IID data clustering

来源：评论

学校读者我要写书评

暂无评论

Contrastive and Non-Contrastive Strategies for Federated Self-Supervised Representation Learning and Deep Clustering

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2024年第6期18卷 1070-1084页

作者： Miao, Runxuan Koyuncu, Erdem Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA

We investigate federated self-supervised representation learning (FedSSRL) and federated clustering (FedCl), aiming to derive low-dimensional representations of datasets distributed across multiple clients, potentially in a heterogeneous manner. Our proposed solutions for both FedSSRL and FedCl involves a comparative analysis from a broad learning context. In particular, we show that a two-stage model, beginning with representation learning and followed by clustering, is an effective learning strategy for both tasks. Notably, integrating a contrastive loss as regularizer significantly boosts performance, even if the task is representation learning. Moreover, for FedCl, a contrastive loss is most effective in both stages, whereas FedSSRL benefits more from a non-contrastive loss. These findings are corroborated by extensive experiments on various image datasets.

关键词： Representation learning Federated learning Data models distributed databases Training Signal processing algorithms Contrastive learning Clustering federated learning representation learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Security and Robustness for Split Federated Learning Against Poisoning Attacks

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 175-190页

作者： Wu, Xiaodong Yuan, Henry Li, Xiangman Ni, Jianbing Lu, Rongxing Queens Univ Ingenu Labs Res Inst Dept Elect & Comp Engn Kingston ON K7L 3N6 Canada Queens Univ Dept Elect & Comp Engn Kingston ON K7L 3N6 Canada Univ New Brunswick Fac Comp Sci Fredericton NB E3B 5A3 Canada

Split federated learning (SFL) is a recently proposed distributed collaborative learning architecture that integrates federated learning (FL) with split learning (SL), offering an ingenious solution for safeguarding privacy in resource-limited environments. Despite the compelling potential of SFL and its appealing attributes, its robustness remains uncharted territory. In this paper, we investigate the security and robustness of SFL, with a specific focus on its susceptibility to malicious client-driven poisoning attacks. Specifically, we study the weaknesses of SFL against the well-known poisoning attacks designed for FL, like dataset poisoning, weight poisoning, and label poisoning. We also introduce a novel type of poisoning attacks tailored for SFL, named smash poisoning, and evaluate the robustness against smash poisoning attacks and advanced hybrid attacks (DatasetSmash, LabelSmash, and WeightSmash) that amalgamate smash poisoning with the other three methods for FL. By simulating these attacks across diverse domains over four datasets, we find that most of these attacks (including weight, WeightSmash, and LabelSmash poisoning) can disrupt the converged models with straightforward poisoning actions or have persistent negative influence on the model accuracy even after the termination of the attacks. Furthermore, our findings reveal that the robustness of SFL can be augmented by strategically adjusting the system parameters, such as client quantity, bottleneck size or split type. Finally, we verify the effectiveness of the typical defense mechanisms of poisoning attacks intended for FL and design a new defense strategy that filters out malicious smashed data to improve the robustness of SFL. We observe that the adoption of properly chosen defense mechanisms is beneficial in decreasing the security risks of SFL, but entirely eliminating the impacts of poisoning attacks in SFL is still challenging.

关键词： Servers Robustness Training Federated learning Data models Computational modeling Security Accuracy distributed databases Data privacy Poisoning attack split federated learning AI robustness

来源：评论

学校读者我要写书评

暂无评论

HFL-TranWGAN: Knowledge-Driven Cross-Domain Collaborative Anomaly Detection for End-to-End Network Slicing

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2025年第1期22卷 760-776页

作者： Wu, Yanfei Liang, Liang Jia, Yunjian Wen, Wanli Chongqing Univ Sch Microelect & Commun Engn Chongqing 400044 Peoples R China

Network slicing is a key technology that can provide service assurance for the heterogeneous application scenarios emerging in the next-generation networks. However, the heterogeneity and complexity of virtualized end-to-end network slicing environments pose challenges for network security operations and management. In this paper, we propose a knowledge-driven cross-domain collaborative anomaly detection scheme for end-to-end network slicing, namely HFL-TranWGAN. Specifically, we first design a hierarchical management framework that performs three-tier hierarchical intelligent management of end-to-end network slices, while introducing a knowledge plane to assist the management plane in making intelligent decisions. Then, we develop a knowledge-driven sub-slice anomaly detection model, the conditional TranWGAN model, in which an encoder, a generator, and multiple discriminators perform adversarial learning simultaneously. Finally, taking the sub-slice anomaly detection model as the basic training model, we utilize hierarchical federated learning to achieve inter-slice and intra-slice collaborative anomaly detection. We calculate the anomaly scores through the discrimination error and reconstruction error to obtain the anomaly detection results. Simulation results on two real-world datasets show that the proposed HFL-TranWGAN scheme performs better in anomaly detection performance such as F1 score and precision compared to the benchmark methods. Specifically, HFL-TranWGAN improved precision by up to 8.53% and F1 score by up to 1.88% compared to benchmarks.

关键词： Anomaly detection Network slicing Collaboration Hidden Markov models Knowledge engineering distributed databases Training Federated learning 3GPP Support vector machines End-to-end network slicing collaborative anomaly detection knowledge-driven generating adversarial networks hierarchical federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Federated Learning Robustness Using Locally Benignity-Assessable Bayesian Dropout

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 2464-2479页

作者： Xue, Jingjing Sun, Sheng Liu, Min Li, Qi Xu, Ke Chinese Acad Sci Inst Comp Technol Beijing 100045 Peoples R China Zhongguancun Lab Beijing 100086 Peoples R China Tsinghua Univ Inst Network Sci & Cyberspace Beijing Peoples R China Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol BNRist Beijing Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100190 Peoples R China

Federated Learning (FL) has emerged as a privacy-preserving training paradigm, which enables distributed devices to jointly learn a shared model without raw data sharing. However, the inaccessible client-side data and unverifiable local training leave FL vulnerable to Byzantine attacks. Most defense strategies focus on penalizing malicious clients in server-side aggregations and ignore clients-side weight units poisoning assessment, failing to maintain robustness and convergence in non-IID settings. In this paper, we propose Federated learning with Benignity-assessable Bayesian Dropout and variational Attention (FedBDA) to achieve local robust training based on fine-grained benignity indicators and guarantee global robustness over non-IID data. Specifically, FedBDA integrates variational inference explanation of dropout into local training, where each client individually quantifies the benign degree of weight units to determine a resilient dropping pattern for the local Bayesian model, enabling client-side robust training with Bayesian interpretability. To accommodate variational distributions of local Bayesian models and globally assess their benign potentials, we design a joint attention mechanism based on Jensen-Shannon divergence among local, global, and median distributions for robust weighted aggregation. Theoretical analysis proves the robustness and convergence of FedBDA. We conduct extensive experiments on four benchmark datasets with five typical attacks, and the results demonstrate that FedBDA outperforms status quo approaches in model performance and running efficiency.

关键词： Bayes methods Training Servers Data models Robustness distributed databases Uplink Convergence Computational modeling Recurrent neural networks Federated learning Byzantine attack dropout defense robust aggregation

来源：评论

学校读者我要写书评

暂无评论

On Collaboration in distributed Parameter Estimation With Resource Constraints

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2025年第1期22卷 151-167页

作者： Chen, Yu-Zhen Janice Menasche, Daniel S. Towsley, Don Univ Massachusetts Amherst Manning Coll Informat & Comp Sci Amherst MA 01002 USA Univ Fed Rio de Janeiro Inst Comp BR-21941901 Rio de Janeiro Brazil

Effective resource allocation in sensor networks, IoT systems, and distributed computing is essential for applications such as environmental monitoring, surveillance, and smart infrastructure. Sensors or agents must optimize their resource allocation to maximize the accuracy of parameter estimation. In this work, we consider a group of sensors or agents, each sampling from a different variable of a multivariate Gaussian distribution and having a different estimation objective. We formulate a sensor or agent's data collection and collaboration policy design problem as a Fisher information maximization (or Cramer-Rao bound minimization) problem. This formulation captures a novel trade-off in energy use, between locally collecting univariate samples and collaborating to produce multivariate samples. When knowledge of the correlation between variables is available, we analytically identify two cases: (1) where the optimal data collection policy entails investing resources to transfer information for collaborative sampling, and (2) where knowledge of the correlation between samples cannot enhance estimation efficiency. When knowledge of certain correlations is unavailable, but collaboration remains potentially beneficial, we propose novel approaches that apply multi-armed bandit algorithms to learn the optimal data collection and collaboration policy in our sequential distributed parameter estimation problem. We illustrate the effectiveness of the proposed algorithms, DOUBLE-F, DOUBLE-Z, UCB-F, UCB-Z, through simulation.

关键词： Collaboration Estimation Data collection Correlation distributed databases Parameter estimation Optimization Vectors Wireless sensor networks Resource management distributed parameter estimation sequential estimation sensor selection vertically partitioned data Fisher information multi-armed bandit (MAB) Kalman filter

来源：评论

学校读者我要写书评

暂无评论

SLAPP: Poisoning Prevention in Federated Learning and Differential Privacy via Stateful Proofs of Execution

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 4167-4182页

作者： Rattanavipanon, Norrathep Nunes, Ivan De Oliveira Prince Songkla Univ Coll Comp Phuket 83120 Thailand Univ Zurich Dept Informat SPINS Grp CH-8006 Zurich Switzerland

The rise of IoT-driven distributed data analytics, coupled with increasing privacy concerns, has led to a demand for effective privacy-preserving and federated data collection/model training mechanisms. In response, approaches such as Federated Learning (FL) and Local Differential Privacy (LDP) have been proposed and attracted much attention over the past few years. However, they still share the common limitation of being vulnerable to poisoning attacks wherein adversaries compromising edge devices feed forged (a.k.a. "poisoned") data to aggregation back-ends, undermining the integrity of FL/LDP results. In this work, we propose a system-level approach to remedy this issue based on a novel security notion of Proofs of Stateful Execution ( PoSX ) for IoT/embedded devices' software. To realize the PoSX concept, we design SLAPP : a System-Level Approach for Poisoning Prevention. SLAPP leverages commodity security features of embedded devices - in particular ARM TrustZone-M security extensions - to verifiably bind raw sensed data to their correct usage as part of FL/LDP edge device routines. As a consequence, it offers robust security guarantees against poisoning. Our evaluation, based on real-world prototypes featuring multiple cryptographic primitives and data collection schemes, showcases SLAPP 's security and low overhead.

关键词： Internet of Things Training Prevention and mitigation Data collection distributed databases Cryptography Vectors Privacy Noise measurement Federated learning Proofs of execution poisoning attacks federated learning local differential privacy embedded systems security

来源：评论

学校读者我要写书评

暂无评论

FedCruise: Collaborative Cruise Guidance With Federated Policy Distillation in Multiple Ride-Hailing Platforms

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第7期12卷 8873-8884页

作者： Sun, Guolin Maale, Gerald Tietaa Zhang, Heng Ayepah-Mensah, Daniel Jiang, Jun Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Natl Key Lab Intelligent Collaborat Comp Chengdu 611730 Peoples R China Naval Univ Engn Dept Operat & Planning Wuhan 430033 Peoples R China

Recent technological advancements have led to the emergence of intelligent cruise guidance systems tailored for ride-hailing platforms (RHPs), such as Uber and Didi Chuxing, offering potential solutions to issues like traffic congestion and vehicle emissions. However, they face challenges, such as passenger-driver matching, route, and price optimization, and ensuring safety and fairness. These challenges are exacerbated by heterogeneity in data across multiple RHPs and privacy concerns related to data sharing. In this article, we propose a novel cruise guidance framework, FedCruise, which tackles these issues by using customized federated policy distillation with deep reinforcement learning (DRL). FedCruise enables collaborative model training across different RHPs without exchanging raw data, preserving privacy while addressing nonidentically distributed (non-IID) data challenges. FedCruise employs two models in each DRL agent: 1) a local teacher model and 2) a global student model, enabling bidirectional learning and achieving a global optimum. Our framework optimizes ride-sharing services and addresses data heterogeneity and privacy challenges. The results of our extensive simulations demonstrate the effectiveness and efficiency of FedCruise, proving its superiority in convergence rate, pickup orders, and driver income over other benchmarks.

关键词： Vehicles Data privacy Data models Collaboration distributed databases Public transportation Internet of Things Vehicle dynamics Convergence Dispatching Car sharing cruise guidance deep reinforcement learning (DRL) federated learning (FL) knowledge distillation ride-hailing

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：