VFedCS: Optimizing Client Selection for Volatile Federated Learning

计算机科学 选择(遗传算法) 服务器 分布式计算 数据库 计算机网络 人工智能
作者
Fang Shi,Chunchao Hu,Weiwei Lin,Lisheng Fan,Tiansheng Huang,Wentai Wu
出处
期刊:IEEE Internet of Things Journal [Institute of Electrical and Electronics Engineers]
卷期号:9 (24): 24995-25010 被引量:20
标识
DOI:10.1109/jiot.2022.3195073
摘要

Federated learning (FL) has shown great potential as a privacy-preserving solution to training a centralized model based on local data from available clients. However, we argue that, over the course of training, the available clients may exhibit some volatility in terms of the client population, client data, and training status. Considering these volatilities, we propose a new learning scenario termed volatile federated learning (volatile FL) featuring set volatility, statistical volatility, and training volatility. The volatile client set along with the dynamic of clients' data and the unreliable nature of clients (e.g., unintentional shutdown and network instability) greatly increase the difficulty of client selection. In this article, we formulate and decompose the global problem into two subproblems based on alternating minimization. For an efficient settlement for the proposed selection problem, we quantify the impact of clients' data and resource heterogeneity for volatile FL and introduce the cumulative effective participation data (CEPD) as an optimization objective. Based on this, we propose upper confidence bound-based greedy selection, dubbed UCB-GS, to address the client selection problem in volatile FL. Theoretically, we prove that the regret of UCB-GS is strictly bounded by a finite constant, justifying its theoretical feasibility. Furthermore, experimental results show that our method significantly reduces the number of training rounds (by up to 62%) while increasing the global model's accuracy by 7.51%.
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
星期八完成签到,获得积分10
刚刚
小王哪跑发布了新的文献求助10
刚刚
天天快乐应助djbj2022采纳,获得10
1秒前
地球观光客完成签到,获得积分10
2秒前
Arctic完成签到,获得积分10
2秒前
1142722发布了新的文献求助10
2秒前
Yiyyan完成签到,获得积分10
2秒前
ghy完成签到 ,获得积分10
3秒前
3秒前
4秒前
WSY完成签到 ,获得积分10
5秒前
小石榴的爸爸完成签到 ,获得积分10
5秒前
Arctic发布了新的文献求助10
5秒前
5秒前
烟花应助tangz采纳,获得10
5秒前
追寻柚子完成签到,获得积分10
8秒前
9秒前
濮阳映萱发布了新的文献求助10
9秒前
hsy发布了新的文献求助10
9秒前
小石榴爸爸完成签到 ,获得积分10
9秒前
艾科研发布了新的文献求助10
10秒前
11秒前
Faded完成签到 ,获得积分10
11秒前
祺屿梦完成签到,获得积分10
12秒前
enternow完成签到 ,获得积分10
12秒前
wynne313完成签到 ,获得积分10
12秒前
深情安青应助hsy采纳,获得10
12秒前
风起_完成签到,获得积分10
12秒前
12秒前
14秒前
djbj2022发布了新的文献求助10
14秒前
奋斗书白完成签到,获得积分10
14秒前
雨雨雨雨发布了新的文献求助10
15秒前
17秒前
jinjin发布了新的文献求助10
17秒前
wu完成签到,获得积分10
17秒前
qin希望应助CatC采纳,获得20
17秒前
程程完成签到,获得积分20
17秒前
Afaq应助OOBRS采纳,获得10
18秒前
专一的白萱完成签到 ,获得积分10
18秒前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
Indomethacinのヒトにおける経皮吸収 400
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 370
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
Aktuelle Entwicklungen in der linguistischen Forschung 300
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 3991212
求助须知:如何正确求助?哪些是违规求助? 3532463
关于积分的说明 11257687
捐赠科研通 3271490
什么是DOI,文献DOI怎么找? 1805436
邀请新用户注册赠送积分活动 882386
科研通“疑难数据库(出版商)”最低求助积分说明 809312