Distributed Online Learning Over Multitask Networks With Rank-One Model

IF 3 3区计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Transactions on Signal and Information Processing over Networks Pub Date : 2025-02-26 DOI:10.1109/TSIPN.2025.3543973

Yitong Chen;Danqi Jin;Jie Chen;Cédric Richard;Wen Zhang;Gongping Huang;Jingdong Chen

{"title":"Distributed Online Learning Over Multitask Networks With Rank-One Model","authors":"Yitong Chen;Danqi Jin;Jie Chen;Cédric Richard;Wen Zhang;Gongping Huang;Jingdong Chen","doi":"10.1109/TSIPN.2025.3543973","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"11 ","pages":"314-328"},"PeriodicalIF":3.0000,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Signal and Information Processing over Networks","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10904872/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文本刊更多论文

基于rank - 1模型的多任务网络分布式在线学习

分布式网络中多任务关系的建模近年来引起了人们极大的兴趣。在本文中，我们提出了一种新的秩一模型，其中所有待估计的最优向量都是待确定的未知向量的缩放版本。在考虑秩一关系的基础上，提出了一个约束集中优化问题，经过解耦处理后，采用投影梯度下降法进行分布式求解。为了对这个投影进行有效的计算，我们建议用计算效率高的幂方法代替密集的奇异值分解。此外，针对同一最优向量的局部估计在邻域内组合，以进一步提高其准确性。对星型拓扑结构进行了理论分析，并推导了保证算法在均方和均方意义上稳定的条件。最后给出了仿真结果，验证了所提算法的有效性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Signal and Information Processing over Networks Computer Science-Computer Networks and Communications

CiteScore

5.80

自引率

12.50%

发文量

期刊介绍： The IEEE Transactions on Signal and Information Processing over Networks publishes high-quality papers that extend the classical notions of processing of signals defined over vector spaces (e.g. time and space) to processing of signals and information (data) defined over networks, potentially dynamically varying. In signal processing over networks, the topology of the network may define structural relationships in the data, or may constrain processing of the data. Topics include distributed algorithms for filtering, detection, estimation, adaptation and learning, model selection, data fusion, and diffusion or evolution of information over such networks, and applications of distributed signal processing.