异构联邦边缘学习的快速收敛:一种自适应聚类数据共享方法

IF 7.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Gang Hu;Yinglei Teng;Nan Wang;Zhu Han
{"title":"异构联邦边缘学习的快速收敛:一种自适应聚类数据共享方法","authors":"Gang Hu;Yinglei Teng;Nan Wang;Zhu Han","doi":"10.1109/TMC.2025.3533566","DOIUrl":null,"url":null,"abstract":"Federated Edge Learning (FEL) emerges as a pioneering distributed machine learning paradigm for the 6 G Hyper-Connectivity, harnessing data from the IoT devices while upholding data privacy. However, current FEL algorithms struggle with non-independent and non-identically distributed (non-IID) data, leading to elevated communication costs and compromised model accuracy. To address these statistical imbalances, we introduce a clustered data sharing framework, mitigating data heterogeneity by selectively sharing partial data from cluster heads to trusted associates through sidelink-aided multicasting. The collective communication pattern is integral to FEL training, where both cluster formation and the efficiency of communication and computation impact training latency and accuracy simultaneously. To tackle the strictly coupled data sharing and resource optimization, we decompose the optimization problem into the clients clustering and effective data sharing subproblems. Specifically, a distribution-based adaptive clustering algorithm (DACA) is devised basing on three deductive cluster forming conditions, which ensures the maximum sharing yield. Meanwhile, we design a stochastic optimization based joint computed frequency and shared data volume optimization (JFVO) algorithm, determining the optimal resource allocation with an uncertain objective function. The experiments show that the proposed framework facilitates FEL on non-IID datasets with faster convergence rate and higher model accuracy in a resource-limited environment.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 6","pages":"5342-5356"},"PeriodicalIF":7.7000,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Faster Convergence on Heterogeneous Federated Edge Learning: An Adaptive Clustered Data Sharing Approach\",\"authors\":\"Gang Hu;Yinglei Teng;Nan Wang;Zhu Han\",\"doi\":\"10.1109/TMC.2025.3533566\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Federated Edge Learning (FEL) emerges as a pioneering distributed machine learning paradigm for the 6 G Hyper-Connectivity, harnessing data from the IoT devices while upholding data privacy. However, current FEL algorithms struggle with non-independent and non-identically distributed (non-IID) data, leading to elevated communication costs and compromised model accuracy. To address these statistical imbalances, we introduce a clustered data sharing framework, mitigating data heterogeneity by selectively sharing partial data from cluster heads to trusted associates through sidelink-aided multicasting. The collective communication pattern is integral to FEL training, where both cluster formation and the efficiency of communication and computation impact training latency and accuracy simultaneously. To tackle the strictly coupled data sharing and resource optimization, we decompose the optimization problem into the clients clustering and effective data sharing subproblems. Specifically, a distribution-based adaptive clustering algorithm (DACA) is devised basing on three deductive cluster forming conditions, which ensures the maximum sharing yield. Meanwhile, we design a stochastic optimization based joint computed frequency and shared data volume optimization (JFVO) algorithm, determining the optimal resource allocation with an uncertain objective function. The experiments show that the proposed framework facilitates FEL on non-IID datasets with faster convergence rate and higher model accuracy in a resource-limited environment.\",\"PeriodicalId\":50389,\"journal\":{\"name\":\"IEEE Transactions on Mobile Computing\",\"volume\":\"24 6\",\"pages\":\"5342-5356\"},\"PeriodicalIF\":7.7000,\"publicationDate\":\"2025-01-24\",\"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/10852368/\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Mobile Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10852368/","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

摘要

联邦边缘学习(FEL)作为6g超连接的开创性分布式机器学习范例出现,在保护数据隐私的同时利用来自物联网设备的数据。然而,目前的FEL算法难以处理非独立和非同分布(non-IID)数据,导致通信成本增加和模型精度降低。为了解决这些统计不平衡问题,我们引入了一个集群数据共享框架,通过旁链辅助多播有选择地将来自集群头的部分数据共享给受信任的伙伴,从而减轻了数据异质性。集体通信模式是FEL训练中不可或缺的一部分,其中簇的形成以及通信和计算的效率同时影响训练的延迟和准确性。为了解决数据共享和资源优化的严格耦合问题,我们将优化问题分解为客户端聚类和有效数据共享子问题。具体而言,基于三种演绎聚类形成条件,设计了一种基于分布的自适应聚类算法(DACA),以保证最大共享产量。同时,设计了一种基于随机优化的联合计算频率和共享数据量优化(JFVO)算法,以不确定的目标函数确定资源的最优分配。实验表明,在资源有限的环境下,该框架能够以更快的收敛速度和更高的模型精度促进非iid数据集上的FEL。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Faster Convergence on Heterogeneous Federated Edge Learning: An Adaptive Clustered Data Sharing Approach
Federated Edge Learning (FEL) emerges as a pioneering distributed machine learning paradigm for the 6 G Hyper-Connectivity, harnessing data from the IoT devices while upholding data privacy. However, current FEL algorithms struggle with non-independent and non-identically distributed (non-IID) data, leading to elevated communication costs and compromised model accuracy. To address these statistical imbalances, we introduce a clustered data sharing framework, mitigating data heterogeneity by selectively sharing partial data from cluster heads to trusted associates through sidelink-aided multicasting. The collective communication pattern is integral to FEL training, where both cluster formation and the efficiency of communication and computation impact training latency and accuracy simultaneously. To tackle the strictly coupled data sharing and resource optimization, we decompose the optimization problem into the clients clustering and effective data sharing subproblems. Specifically, a distribution-based adaptive clustering algorithm (DACA) is devised basing on three deductive cluster forming conditions, which ensures the maximum sharing yield. Meanwhile, we design a stochastic optimization based joint computed frequency and shared data volume optimization (JFVO) algorithm, determining the optimal resource allocation with an uncertain objective function. The experiments show that the proposed framework facilitates FEL on non-IID datasets with faster convergence rate and higher model accuracy in a resource-limited environment.
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
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