为提高通信效率的联合学习选择贪婪的沙普利客户端

Pranava Singhal;Shashi Raj Pandey;Petar Popovski
{"title":"为提高通信效率的联合学习选择贪婪的沙普利客户端","authors":"Pranava Singhal;Shashi Raj Pandey;Petar Popovski","doi":"10.1109/LNET.2024.3363620","DOIUrl":null,"url":null,"abstract":"The standard client selection algorithms for Federated Learning (FL) are often unbiased and involve uniform random sampling of clients. This has been proven sub-optimal for fast convergence under practical settings characterized by significant heterogeneity in data distribution, computing, and communication resources across clients. For applications having timing constraints due to limited communication opportunities with the parameter server (PS), the client selection strategy is critical to complete model training within the fixed budget of communication rounds. To address this, we develop a biased client selection strategy, GreedyFed, that identifies and greedily selects the most contributing clients in each communication round. This method builds on a fast approximation algorithm for the Shapley Value at the PS, making the computation tractable for real-world applications with many clients. Compared to various client selection strategies on several real-world datasets, GreedyFed demonstrates fast and stable convergence with high accuracy under timing constraints and when imposing a higher degree of heterogeneity in data distribution, systems constraints, and privacy requirements.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 2","pages":"134-138"},"PeriodicalIF":0.0000,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Greedy Shapley Client Selection for Communication-Efficient Federated Learning\",\"authors\":\"Pranava Singhal;Shashi Raj Pandey;Petar Popovski\",\"doi\":\"10.1109/LNET.2024.3363620\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The standard client selection algorithms for Federated Learning (FL) are often unbiased and involve uniform random sampling of clients. This has been proven sub-optimal for fast convergence under practical settings characterized by significant heterogeneity in data distribution, computing, and communication resources across clients. For applications having timing constraints due to limited communication opportunities with the parameter server (PS), the client selection strategy is critical to complete model training within the fixed budget of communication rounds. To address this, we develop a biased client selection strategy, GreedyFed, that identifies and greedily selects the most contributing clients in each communication round. This method builds on a fast approximation algorithm for the Shapley Value at the PS, making the computation tractable for real-world applications with many clients. Compared to various client selection strategies on several real-world datasets, GreedyFed demonstrates fast and stable convergence with high accuracy under timing constraints and when imposing a higher degree of heterogeneity in data distribution, systems constraints, and privacy requirements.\",\"PeriodicalId\":100628,\"journal\":{\"name\":\"IEEE Networking Letters\",\"volume\":\"6 2\",\"pages\":\"134-138\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Networking Letters\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10427554/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Networking Letters","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10427554/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

联邦学习(FL)的标准客户机选择算法通常是无偏的,涉及客户机的均匀随机抽样。这已被证明是在客户端数据分布、计算和通信资源存在显著异质性的实际环境下实现快速收敛的次优方法。对于因与参数服务器(PS)的通信机会有限而受到时间限制的应用,客户端选择策略对于在固定的通信回合预算内完成模型训练至关重要。为了解决这个问题,我们开发了一种有偏差的客户端选择策略--GreedyFed,它能在每轮通信中识别并贪婪地选择贡献最大的客户端。这种方法建立在 PS Shapley 值的快速近似算法基础上,使得计算对于有许多客户端的实际应用变得简单易行。在多个真实世界数据集上,与各种客户端选择策略相比,GreedyFed 在时间限制条件下,以及在数据分布、系统限制和隐私要求方面施加更高的异质性时,都表现出了快速、稳定的收敛性和高准确性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Greedy Shapley Client Selection for Communication-Efficient Federated Learning
The standard client selection algorithms for Federated Learning (FL) are often unbiased and involve uniform random sampling of clients. This has been proven sub-optimal for fast convergence under practical settings characterized by significant heterogeneity in data distribution, computing, and communication resources across clients. For applications having timing constraints due to limited communication opportunities with the parameter server (PS), the client selection strategy is critical to complete model training within the fixed budget of communication rounds. To address this, we develop a biased client selection strategy, GreedyFed, that identifies and greedily selects the most contributing clients in each communication round. This method builds on a fast approximation algorithm for the Shapley Value at the PS, making the computation tractable for real-world applications with many clients. Compared to various client selection strategies on several real-world datasets, GreedyFed demonstrates fast and stable convergence with high accuracy under timing constraints and when imposing a higher degree of heterogeneity in data distribution, systems constraints, and privacy requirements.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
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