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
刚刚
刚刚
kaisim完成签到,获得积分20
1秒前
1秒前
慕青应助hugdoggy采纳,获得10
2秒前
2秒前
遮宁完成签到,获得积分10
2秒前
xiaozhang完成签到,获得积分10
3秒前
justsoso完成签到,获得积分10
3秒前
YANHAN发布了新的文献求助10
3秒前
4秒前
kaisim发布了新的文献求助10
4秒前
XM完成签到 ,获得积分10
5秒前
赘婿应助Sam采纳,获得10
5秒前
nano完成签到 ,获得积分10
5秒前
文献蚂蚁发布了新的文献求助10
6秒前
LiDaYang完成签到,获得积分10
6秒前
阿辉发布了新的文献求助10
6秒前
xiaozhang发布了新的文献求助10
7秒前
Lion完成签到,获得积分10
7秒前
zhangyu应助jiang采纳,获得10
7秒前
苏苏弋完成签到,获得积分10
8秒前
存慎完成签到 ,获得积分10
8秒前
baba小天后发布了新的文献求助10
8秒前
浦老四完成签到,获得积分10
8秒前
今天进步了吗完成签到,获得积分10
8秒前
黄汤圆发布了新的文献求助20
9秒前
9秒前
hhhhhhh完成签到,获得积分10
10秒前
Planck完成签到,获得积分10
10秒前
认真小海豚完成签到,获得积分10
10秒前
11秒前
叫我一只球完成签到,获得积分10
11秒前
深海鱼完成签到,获得积分10
11秒前
11秒前
三木完成签到 ,获得积分10
12秒前
小明发布了新的文献求助10
12秒前
12秒前
Hello应助文献蚂蚁采纳,获得10
13秒前
13秒前
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 4009366
求助须知:如何正确求助?哪些是违规求助? 3549232
关于积分的说明 11301348
捐赠科研通 3283689
什么是DOI,文献DOI怎么找? 1810387
邀请新用户注册赠送积分活动 886217
科研通“疑难数据库(出版商)”最低求助积分说明 811301