IEEE Transactions on Network Science and Engineering最新文献

Degradation Estimation for Distributed Nonlinear Systems: A PDF-Consensus Particle Filtering Method

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-29 DOI: 10.1109/TNSE.2025.3530158

Chulin Zhou;Shiyou Chen;Chaoyang Wang

{"title":"Degradation Estimation for Distributed Nonlinear Systems: A PDF-Consensus Particle Filtering Method","authors":"Chulin Zhou;Shiyou Chen;Chaoyang Wang","doi":"10.1109/TNSE.2025.3530158","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3530158","url":null,"abstract":"In this article, a distributed probability density function (PDF)-consensus particle filter (PF) algorithm for a class of network systems with degradation is discussed. In order to consider the interaction between component-level degradation and system state, the degradation modelling framework is developed by combining the stochastic degradation process and the state transition model of the system. And the dynamics of the degradation model are described in terms of a Wiener-based process to emphasize the evolution of degradation over time. To reach consensus on the local posterior PDFs at each node in the sense of relative entropy and reduce the communication burden, the state space of the system is divided by a group of weighted grids. Then, the local PDFs are approximated with a combination of the indicator functions and exchange the parameters with neighboring nodes. In order to obtain the particle representation of the fused PDFs, a new importance sampling function is developed to fuse the local grid-based PDFs and to enhance the compatibility of particles with neighboring nodes. A numerical example on target tracking is provided to demonstrate the effectiveness of the proposed scheme.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1408-1419"},"PeriodicalIF":6.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Hybrid Semi-Asynchronous Federated Learning and Split Learning Strategy in Edge Networks 边缘网络中的混合半异步联合学习和拆分学习策略

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-22 DOI: 10.1109/TNSE.2025.3530999

Neha Singh;Mainak Adhikari

{"title":"A Hybrid Semi-Asynchronous Federated Learning and Split Learning Strategy in Edge Networks","authors":"Neha Singh;Mainak Adhikari","doi":"10.1109/TNSE.2025.3530999","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3530999","url":null,"abstract":"Federated Learning (FL) is an emerging technique that involves training Machine/Deep Learning models over distributed Edge Devices (EDs) while facing three challenges: device heterogeneity, resource-constraint devices, and Non-IID (Non-Identically Independently Distributed). In the standard FL, the centralized server has to wait for the model parameters from the slowest participating EDs for global training, which leads to increased waiting time due to device heterogeneity. Asynchronous FL resolves the issue of device heterogeneity, however, it requires frequent model parameter transfer, resulting in a straggler effect. Further, frequent asynchronous updates over Non-IID in participating EDs can affect training accuracy. To overcome the challenges, in this paper, we present a new Federated Semi-Asynchronous Split Learning (Fed-SASL) strategy. Fed-SASL utilizes semi-asynchronous aggregation, where model parameters are aggregated in a centralized cloud server, and received from participating EDs without waiting for all devices. This strategy significantly reduces training time and communication overhead. Additionally, split learning is employed to handle slow EDs by dividing the neural network model based on the computational loads of devices, thereby reducing the burden on stragglers. Extensive simulation results over real-time testbed and one benchmark dataset demonstrate the effectiveness of the proposed strategy over existing ones.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1429-1439"},"PeriodicalIF":6.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Hybrid Multi-Agent System Approach for Distributed Composite Convex Optimization Under Unbalanced Directed Graphs 非平衡有向图下分布式复合凸优化的混合多代理系统方法

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-17 DOI: 10.1109/TNSE.2025.3527466

Zhu Wang;Dong Wang;Xiaopeng Xu;Jie Lian

引用次数: 0

Supporting Self-Management Redactable Blockchain With Double-Auditability and Revocability for IoT

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-16 DOI: 10.1109/TNSE.2025.3529030

Xiuhua Lu;Yuhao Hou;Jiazheng Zou;Jing Liu;Xijie Lu

引用次数: 0

Distributed ADMM With Linear Updates Over Directed Networks 有向网络上线性更新的分布式 ADMM

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-16 DOI: 10.1109/TNSE.2025.3529703

Kiran Rokade;Rachel Kalpana Kalaimani

{"title":"Distributed ADMM With Linear Updates Over Directed Networks","authors":"Kiran Rokade;Rachel Kalpana Kalaimani","doi":"10.1109/TNSE.2025.3529703","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3529703","url":null,"abstract":"Distributed optimization over a network of agents is ubiquitous in applications such as power system, robotics and statistical learning. In many settings, the communication network is directed, i.e., the communication links between agents are unidirectional. While several variations of gradient-descent-based primal methods have been proposed for distributed optimization over directed networks, an extension of dual-ascent methods to directed networks remains a less-explored area. In this paper, we propose a distributed version of the Alternating Direction Method of Multipliers (ADMM) with linear updates for directed networks using balancing weights, called BW-DADMM (Balancing Weights Directed ADMM). We show that if the objective function of the minimization problem is smooth and strongly convex, then BW-DADMM achieves a geometric rate of convergence to the optimal point. Our algorithm exploits the robustness inherent to ADMM by not enforcing accurate consensus, thereby significantly improving the convergence rate. We illustrate this by numerical examples, where we compare the performance of BW-DADMM with that of state-of-the-art ADMM methods over directed graphs.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1396-1407"},"PeriodicalIF":6.7,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Weighted Average Consensus Algorithms in Distributed and Federated Learning

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-16 DOI: 10.1109/TNSE.2025.3528982

Bernardo Camajori Tedeschini;Stefano Savazzi;Monica Nicoli

{"title":"Weighted Average Consensus Algorithms in Distributed and Federated Learning","authors":"Bernardo Camajori Tedeschini;Stefano Savazzi;Monica Nicoli","doi":"10.1109/TNSE.2025.3528982","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3528982","url":null,"abstract":"The exponential growth of the Internet of Things (IoT) has created an essential demand for Distributed Machine Learning (DML) systems. In this context, Federated Learning (FL) allows IoT devices to collaboratively train models while maintaining data ownership and privacy. Despite the evident advantages, FL faces practical challenges such as client selection and adaptation to heterogeneous data distributions. Recently, consensus-driven algorithms have been proposed to enable efficient and scalable FL without a central coordinating entity. Weighted Average Consensus (WAC) tools, primarily used in distributed signal processing, fail to address FL-specific challenges. The paper proposes a new family of server-less FL algorithms optimized to exploit WAC techniques. In particular, we propose an evolution of the centralized Federated Adaptive Weighting (FedAdp) method and present three distinct WAC schemes specifically designed for non-Independent and Identical Distributed (IID) data. Each scheme has a unique aggregation part that optimizes the weights of the clients' local models. The performances are evaluated in a real-world IoT system, analyzing their convergence properties in the context of heterogeneous client populations. Results show that the proposed algorithms outperform vanilla consensus FL up to 56% of accuracy and they are resilient to both label and sample data skewness.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1369-1382"},"PeriodicalIF":6.7,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Revenue-Oriented Optimal Service Offloading Based on Fog-Cloud Collaboration in SD-WAN Enabled Manufacturing Networks 在支持 SD-WAN 的制造网络中基于雾-云协作的以收益为导向的优化服务卸载

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-15 DOI: 10.1109/TNSE.2025.3526750

Xu Chen;Yi Zhang;Chunxiao Jiang;Changqiao Xu;Zhenhui Yuan;Gabriel-Miro Muntean

{"title":"Revenue-Oriented Optimal Service Offloading Based on Fog-Cloud Collaboration in SD-WAN Enabled Manufacturing Networks","authors":"Xu Chen;Yi Zhang;Chunxiao Jiang;Changqiao Xu;Zhenhui Yuan;Gabriel-Miro Muntean","doi":"10.1109/TNSE.2025.3526750","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3526750","url":null,"abstract":"The software-defined wide area network (SD-WAN) is considered one of the most promising paradigms for next generation manufacturing networks. However, SD-WAN users usually suffer from significant delays due to remotely deployed cloud centers. The requirements of delay-sensitive business services make optimal resource allocation methods very important. In this paper, we propose a revenue-oriented service offloading method to improve the efficiency of SD-WAN enabled manufacturing networks through fog-cloud collaboration. To maximize the service revenue, we formulate a coupled combinatorial optimization model to allocate computation and communication resources jointly between the fog node and the cloud. To solve this problem, we propose a service offloading method based on the counterfactual regret minimization (CFR) principle according to the dynamic workload state of the fog nodes. This method reduces the time complexity of problem-solving from exponential to polynomial, and achieves good performance that is very close to the optimal solution in terms of service efficiency. The outstanding contribution of this paper is to unify the multi-objective problem to the revenue scale for optimization to improve the overall service revenue of the SD-WAN. The simulation results show that our method outperforms benchmark methods in terms of both effectiveness and efficiency.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1237-1249"},"PeriodicalIF":6.7,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust Stability and Stabilization of Switched Hyper-Networked Evolutionary Games 交换式超网络演化博弈的稳健性和稳定性

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-15 DOI: 10.1109/TNSE.2025.3530508

Qiutong Zhang;Yuanhua Wang;Ying Wang;Zaihua Xu

引用次数: 0

Label-Flipping Attacks in GNN-Based Federated Learning

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-15 DOI: 10.1109/TNSE.2025.3528831

Shanqing Yu;Jie Shen;Shaocong Xu;Jinhuan Wang;Zeyu Wang;Qi Xuan

{"title":"Label-Flipping Attacks in GNN-Based Federated Learning","authors":"Shanqing Yu;Jie Shen;Shaocong Xu;Jinhuan Wang;Zeyu Wang;Qi Xuan","doi":"10.1109/TNSE.2025.3528831","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3528831","url":null,"abstract":"Federated learning offers multi-party collaborative training but also poses several potential security risks. These security issues have been studied more extensively in the context of basic image models, but it is relatively less explored in the field of graphs. Compared to various existing graph-based attack methods, the label-flipping attack does not need to change the graph structure and it is highly stealthy. Therefore, this paper explores a Graph Federated Label Flipping Attack (Graph-FLFA) and proposes a new malicious gradient computation strategy for federated graph models. The goal of this attack method is to maximally disrupt the classification results of specific nodes in the node classification task, without affecting the classification performance of other nodes. This strategy exhibits strong specificity and stealthiness, effectively balancing the influence of various labels and ensuring significant attack effects even when the poisoning ratio is very low. Extensive experiments on four benchmark datasets demonstrate that Graph-FLFA has a high attack success rate in different GNN-based models, achieving the most advanced attack performance. Furthermore, it has the capability to evade detection methods employed in defensive measures.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1357-1368"},"PeriodicalIF":6.7,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Recursive Remote State Estimation for Stochastic Complex Networks With Degraded Measurements and Amplify-and-Forward Relays 具有退化测量和放大-前向中继的随机复杂网络的递归远程状态估计

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-01-15 DOI: 10.1109/TNSE.2025.3528768

Tong-Jian Liu;Zidong Wang;Yang Liu;Rui Wang

引用次数: 0