Stabilizing and improving federated learning with highly non-iid data and client dropout

IF 3.4 2区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Jian Xu, Meilin Yang, Wenbo Ding, Shao-Lun Huang
{"title":"Stabilizing and improving federated learning with highly non-iid data and client dropout","authors":"Jian Xu,&nbsp;Meilin Yang,&nbsp;Wenbo Ding,&nbsp;Shao-Lun Huang","doi":"10.1007/s10489-024-05956-3","DOIUrl":null,"url":null,"abstract":"<div><p>The label distribution skew has been shown to be a significant obstacle that limits the model performance in federated learning (FL). This challenge could be more serious when the participating clients are in unstable network circumstances and drop out frequently. Previous works have demonstrated that the classifier head is particularly sensitive to the label skew. Therefore, maintaining a balanced classifier head is of significant importance for building a good and unbiased global model. To this end, we propose a simple yet effective framework by introducing a calibrated softmax function with smoothed prior for computing the cross-entropy loss, and a prototype-based feature augmentation scheme to re-balance the local training, which provide a new perspective on tackling the label distribution skew in FL and are lightweight for edge devices and can facilitate the global model aggregation. With extensive experiments on two benchmark classification tasks of Fashion-MNIST and CIFAR-10, our numerical results demonstrate that our proposed method can consistently outperform the baselines, 2 8% of accuracy over FedAvg in the presence of severe label skew and client dropout.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 3","pages":""},"PeriodicalIF":3.4000,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Intelligence","FirstCategoryId":"94","ListUrlMain":"https://link.springer.com/article/10.1007/s10489-024-05956-3","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

The label distribution skew has been shown to be a significant obstacle that limits the model performance in federated learning (FL). This challenge could be more serious when the participating clients are in unstable network circumstances and drop out frequently. Previous works have demonstrated that the classifier head is particularly sensitive to the label skew. Therefore, maintaining a balanced classifier head is of significant importance for building a good and unbiased global model. To this end, we propose a simple yet effective framework by introducing a calibrated softmax function with smoothed prior for computing the cross-entropy loss, and a prototype-based feature augmentation scheme to re-balance the local training, which provide a new perspective on tackling the label distribution skew in FL and are lightweight for edge devices and can facilitate the global model aggregation. With extensive experiments on two benchmark classification tasks of Fashion-MNIST and CIFAR-10, our numerical results demonstrate that our proposed method can consistently outperform the baselines, 2 8% of accuracy over FedAvg in the presence of severe label skew and client dropout.

Abstract Image

稳定和改进具有高度非id数据和客户端退出的联邦学习
标签分布偏差已被证明是限制联邦学习(FL)模型性能的一个重要障碍。当参与的客户端处于不稳定的网络环境中并且经常退出时,这个挑战可能会更加严重。以前的工作已经证明,分类器头部对标签倾斜特别敏感。因此,保持一个平衡的分类器头部对于建立一个良好的、无偏的全局模型是非常重要的。为此,我们提出了一个简单而有效的框架,通过引入一个具有平滑先验的校准softmax函数来计算交叉熵损失,以及一个基于原型的特征增强方案来重新平衡局部训练,这为解决FL中的标签分布倾斜提供了一个新的视角,并且对于边缘设备来说是轻量级的,可以促进全局模型聚合。通过对Fashion-MNIST和CIFAR-10两个基准分类任务的大量实验,我们的数值结果表明,我们提出的方法可以持续优于基线,在存在严重标签倾斜和客户退出的情况下,比fedag的准确率高出28%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Applied Intelligence
Applied Intelligence 工程技术-计算机:人工智能
CiteScore
6.60
自引率
20.80%
发文量
1361
审稿时长
5.9 months
期刊介绍: With a focus on research in artificial intelligence and neural networks, this journal addresses issues involving solutions of real-life manufacturing, defense, management, government and industrial problems which are too complex to be solved through conventional approaches and require the simulation of intelligent thought processes, heuristics, applications of knowledge, and distributed and parallel processing. The integration of these multiple approaches in solving complex problems is of particular importance. The journal presents new and original research and technological developments, addressing real and complex issues applicable to difficult problems. It provides a medium for exchanging scientific research and technological achievements accomplished by the international community.
×
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