CSTAR-FL: Stochastic Client Selection for Tree All-Reduce Federated Learning

IF 7.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Zimu Xu;Antonio Di Maio;Eric Samikwa;Torsten Braun
{"title":"CSTAR-FL: Stochastic Client Selection for Tree All-Reduce Federated Learning","authors":"Zimu Xu;Antonio Di Maio;Eric Samikwa;Torsten Braun","doi":"10.1109/TMC.2024.3507381","DOIUrl":null,"url":null,"abstract":"Federated Learning (FL) is widely applied in privacy-sensitive domains, such as healthcare, finance, and education, due to its privacy-preserving properties. However, implementing FL in dynamic wireless networks poses substantial communication challenges. Central to these challenges is the need for efficient communication strategies that can adapt to fluctuating network conditions and the growing number of participating devices, which can lead to unacceptable communication delays. In this article, we propose Stochastic Client Selection for Tree All-Reduce Federated Learning (<monospace>CSTAR-FL</monospace>), a novel approach that combines a probabilistic User Device (UD) selection strategy with a tree-based communication architecture to enhance communication efficiency in FL within densely populated wireless networks. By optimizing UD selection for effective model aggregation and employing an efficient data transmission structure, <monospace>CSTAR-FL</monospace> significantly reduces communication time and improves FL efficiency. Additionally, our approach ensures high global model accuracy under scenarios where data distribution is heterogeneous from User Device (UD)s. Extensive simulations in dynamic wireless network scenarios demonstrate that <monospace>CSTAR-FL</monospace> outperforms existing state-of-the-art methods, reducing model convergence time by up to 40% without losing the global model accuracy. This makes <monospace>CSTAR-FL</monospace> a robust solution for efficient and scalable FL deployments in high-density environments.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 4","pages":"3110-3129"},"PeriodicalIF":7.7000,"publicationDate":"2024-12-02","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/10772375/","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) is widely applied in privacy-sensitive domains, such as healthcare, finance, and education, due to its privacy-preserving properties. However, implementing FL in dynamic wireless networks poses substantial communication challenges. Central to these challenges is the need for efficient communication strategies that can adapt to fluctuating network conditions and the growing number of participating devices, which can lead to unacceptable communication delays. In this article, we propose Stochastic Client Selection for Tree All-Reduce Federated Learning (CSTAR-FL), a novel approach that combines a probabilistic User Device (UD) selection strategy with a tree-based communication architecture to enhance communication efficiency in FL within densely populated wireless networks. By optimizing UD selection for effective model aggregation and employing an efficient data transmission structure, CSTAR-FL significantly reduces communication time and improves FL efficiency. Additionally, our approach ensures high global model accuracy under scenarios where data distribution is heterogeneous from User Device (UD)s. Extensive simulations in dynamic wireless network scenarios demonstrate that CSTAR-FL outperforms existing state-of-the-art methods, reducing model convergence time by up to 40% without losing the global model accuracy. This makes CSTAR-FL a robust solution for efficient and scalable FL deployments in high-density environments.
联合学习(FL)因其保护隐私的特性,被广泛应用于医疗、金融和教育等对隐私敏感的领域。然而,在动态无线网络中实施联合学习会带来巨大的通信挑战。这些挑战的核心是需要高效的通信策略,以适应不断变化的网络条件和不断增加的参与设备数量,这可能会导致不可接受的通信延迟。在本文中,我们提出了用于树状全还原联合学习(CSTAR-FL)的随机客户端选择,这是一种新颖的方法,它将概率用户设备(UD)选择策略与基于树状的通信架构相结合,以提高人口稠密无线网络中 FL 的通信效率。通过优化 UD 选择以实现有效的模型聚合,并采用高效的数据传输结构,CSTAR-FL 大幅缩短了通信时间,提高了 FL 效率。此外,我们的方法还能确保在用户设备(UD)数据分布异构的情况下,全局模型的高准确性。在动态无线网络场景中进行的大量仿真表明,CSTAR-FL 优于现有的最先进方法,在不损失全局模型精度的情况下,模型收敛时间最多可缩短 40%。这使得 CSTAR-FL 成为在高密度环境中高效、可扩展 FL 部署的强大解决方案。
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 Mobile Computing
IEEE Transactions on Mobile Computing 工程技术-电信学
CiteScore
12.90
自引率
2.50%
发文量
403
审稿时长
6.6 months
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.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信