清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

FedSTS: A Stratified Client Selection Framework for Consistently Fast Federated Learning

选择(遗传算法) 计算机科学 分层抽样 联合学习 分布式计算 机器学习 统计 数学
作者
Dehong Gao,Duanxiao Song,Guangyuan Shen,Xiaoyan Cai,Libin Yang,Gongshen Liu,Xiaoyong Li,Zhen Wang
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:: 1-15
标识
DOI:10.1109/tnnls.2024.3438843
摘要

In this article, we investigate random client selection in the context of horizontal federated learning (FL), whereby only a randomly selected subset of clients transmit their model updates to the server instead of yielding all clients involved. Many researchers have demonstrated that clustering-based client selection constitutes a simple yet efficacious approach to the identification of those clients possessing representative gradient information. Despite the extensive body of research on modified selection methodologies, the majority of prior work is predicated upon the assumption of consistently effective clustering. However, raw gradient-based clustering methods are subject to several challenges: 1) poor effectiveness, the raw high-dimensional gradient of a client is too complex to serve as an appropriate feature for grouping, resulting in large intra-cluster distances and 2) fluctuating effectiveness, due to inherent limitations in clustering, the effectiveness can vary significantly, leading to clusters with diverse levels of heterogeneity. In practice, suboptimal and inconsistent clustering effects can result in clusters with low intra-cluster similarity among clients. The selection of clients from such clusters may impede the overall convergence of training. In this article, we propose, a novel client selection scheme to accelerate the FL convergence by variance reduction. The main idea of is to stratify a compressed model update in order to ensure an excellent grouping effect, and at the same time reduce the cross-client variance by re-allocating the sample chance among different groups based on their diverse heterogeneity. It strikes this convergence acceleration by paying more attention to those client groups with relatively low similarity and then improving the representativeness of the selected subset as much as possible. Theoretically, we demonstrate the critical improvement of the proposed scheme in variance reduction and present equivalence conditions among different client selection methods. We also present the tighter convergence guarantee of the proposed method thanks to the variance reduction. Experimental results confirm the exceeded efficiency of our approach compared to alternatives.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
天天快乐应助JJ采纳,获得10
10秒前
Leofar完成签到 ,获得积分10
12秒前
14秒前
18秒前
JJ完成签到,获得积分10
19秒前
香蕉觅云应助wmuzhao采纳,获得10
21秒前
JJ发布了新的文献求助10
22秒前
顺利问玉完成签到 ,获得积分10
23秒前
25秒前
麦麦完成签到,获得积分10
27秒前
江江完成签到,获得积分10
27秒前
量子星尘发布了新的文献求助30
38秒前
k001boyxw完成签到,获得积分10
44秒前
53秒前
wmuzhao发布了新的文献求助10
58秒前
一苇以航完成签到 ,获得积分10
59秒前
1分钟前
Decade2021完成签到,获得积分10
1分钟前
FashionBoy应助斯文的友菱采纳,获得10
1分钟前
852应助wmuzhao采纳,获得10
1分钟前
1分钟前
1分钟前
下午好完成签到 ,获得积分10
1分钟前
1分钟前
liu完成签到 ,获得积分10
1分钟前
沙海沉戈完成签到,获得积分0
2分钟前
量子星尘发布了新的文献求助10
2分钟前
2分钟前
刘刘完成签到 ,获得积分10
2分钟前
时尚丹寒完成签到 ,获得积分10
2分钟前
大轩完成签到 ,获得积分10
2分钟前
聪明的大树完成签到,获得积分10
3分钟前
3分钟前
深情安青应助科研通管家采纳,获得20
3分钟前
大个应助快乐的惜儿采纳,获得10
3分钟前
3分钟前
xingsixs完成签到 ,获得积分10
3分钟前
kmzzy完成签到,获得积分10
3分钟前
lu发布了新的文献求助10
3分钟前
海洋岩土12138完成签到 ,获得积分10
3分钟前
高分求助中
【提示信息,请勿应助】关于scihub 10000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Social Research Methods (4th Edition) by Maggie Walter (2019) 2390
A new approach to the extrapolation of accelerated life test data 1000
北师大毕业论文 基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 390
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Robot-supported joining of reinforcement textiles with one-sided sewing heads 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4008493
求助须知:如何正确求助?哪些是违规求助? 3548198
关于积分的说明 11298711
捐赠科研通 3282912
什么是DOI,文献DOI怎么找? 1810274
邀请新用户注册赠送积分活动 885976
科研通“疑难数据库(出版商)”最低求助积分说明 811209