Xinyi Hu;Zihan Chen;Chenyuan Feng;Geyong Min;Tony Q. S. Quek;Howard H. Yang
{"title":"Sparsified Random Partial Model Update for Personalized Federated Learning","authors":"Xinyi Hu;Zihan Chen;Chenyuan Feng;Geyong Min;Tony Q. S. Quek;Howard H. Yang","doi":"10.1109/TMC.2024.3507286","DOIUrl":null,"url":null,"abstract":"Federated Learning (FL) stands as a privacy-preserving machine learning paradigm that enables collaborative training of a global model across multiple clients. However, the practical implementation of FL models often confronts challenges arising from data heterogeneity and limited communication resources. To address the aforementioned issues simultaneously, we develop a Sparsified Random Partial Update framework for personalized Federated Learning (<monospace>SRP-pFed</monospace>), which builds upon the foundation of dynamic partial model updates. Specifically, we decouple the local model into personal and shared parts to achieve personalization. For each client, the ratio of its personal part associated with the local model, referred to as the update rate, is regularly renewed over the training procedure via a random walk process endowed with reinforced memory. In each global iteration, clients are clustered into different groups where the ones in the same group share a common update rate. Benefiting from such design, <monospace>SRP-pFed</monospace> realizes model personalization while substantially reducing communication costs in the uplink transmissions. We conduct extensive experiments on various training tasks with diverse heterogeneous data settings. The results demonstrate that the <monospace>SRP-pFed</monospace> consistently outperforms the state-of-the-art methods in test accuracy and communication efficiency.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 4","pages":"3076-3091"},"PeriodicalIF":7.7000,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Mobile Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10769577/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Federated Learning (FL) stands as a privacy-preserving machine learning paradigm that enables collaborative training of a global model across multiple clients. However, the practical implementation of FL models often confronts challenges arising from data heterogeneity and limited communication resources. To address the aforementioned issues simultaneously, we develop a Sparsified Random Partial Update framework for personalized Federated Learning (SRP-pFed), which builds upon the foundation of dynamic partial model updates. Specifically, we decouple the local model into personal and shared parts to achieve personalization. For each client, the ratio of its personal part associated with the local model, referred to as the update rate, is regularly renewed over the training procedure via a random walk process endowed with reinforced memory. In each global iteration, clients are clustered into different groups where the ones in the same group share a common update rate. Benefiting from such design, SRP-pFed realizes model personalization while substantially reducing communication costs in the uplink transmissions. We conduct extensive experiments on various training tasks with diverse heterogeneous data settings. The results demonstrate that the SRP-pFed consistently outperforms the state-of-the-art methods in test accuracy and communication efficiency.
期刊介绍:
IEEE Transactions on Mobile Computing addresses key technical issues related to various aspects of mobile computing. This includes (a) architectures, (b) support services, (c) algorithm/protocol design and analysis, (d) mobile environments, (e) mobile communication systems, (f) applications, and (g) emerging technologies. Topics of interest span a wide range, covering aspects like mobile networks and hosts, mobility management, multimedia, operating system support, power management, online and mobile environments, security, scalability, reliability, and emerging technologies such as wearable computers, body area networks, and wireless sensor networks. The journal serves as a comprehensive platform for advancements in mobile computing research.