FL-Joint: joint aligning features and labels in federated learning for data heterogeneity

IF 5 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Wenxin Chen, Jinrui Zhang, Deyu Zhang
{"title":"FL-Joint: joint aligning features and labels in federated learning for data heterogeneity","authors":"Wenxin Chen, Jinrui Zhang, Deyu Zhang","doi":"10.1007/s40747-024-01636-4","DOIUrl":null,"url":null,"abstract":"<p>Federated learning is a distributed machine learning paradigm that trains a shared model using data from various clients, it faces a core challenge in data heterogeneity arising from diverse client settings and environments. Existing methods typically focus on weight divergence mitigation and aggregation strategy enhancements, they overlook the mixed skew in label and feature distributions prevalent in real-world data. To address this, we present <b><i>FL-Joint</i></b>, a federated learning framework that aligns label and feature distributions using auxiliary loss functions. This framework involves a class-balanced classifier as the local model. It aligns label and feature distributions locally by using auxiliary loss functions based on class-conditional information and pseudo-labels. This alignment drives client feature distributions to converge towards a shared feature space, refining decision boundaries and boosting the global model’s generalization ability. Extensive experiments across diverse datasets and heterogeneous data settings show that our method significantly improves accuracy and convergence speed compared to baseline approaches.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"6 1","pages":""},"PeriodicalIF":5.0000,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Complex & Intelligent Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s40747-024-01636-4","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Federated learning is a distributed machine learning paradigm that trains a shared model using data from various clients, it faces a core challenge in data heterogeneity arising from diverse client settings and environments. Existing methods typically focus on weight divergence mitigation and aggregation strategy enhancements, they overlook the mixed skew in label and feature distributions prevalent in real-world data. To address this, we present FL-Joint, a federated learning framework that aligns label and feature distributions using auxiliary loss functions. This framework involves a class-balanced classifier as the local model. It aligns label and feature distributions locally by using auxiliary loss functions based on class-conditional information and pseudo-labels. This alignment drives client feature distributions to converge towards a shared feature space, refining decision boundaries and boosting the global model’s generalization ability. Extensive experiments across diverse datasets and heterogeneous data settings show that our method significantly improves accuracy and convergence speed compared to baseline approaches.

FL-Joint:数据异构联合学习中的特征和标签联合对齐
联合学习是一种分布式机器学习范式,它利用来自不同客户端的数据训练一个共享模型,它面临的核心挑战是不同客户端设置和环境所产生的数据异质性。现有方法通常侧重于权重发散缓解和聚合策略增强,却忽视了现实世界数据中普遍存在的标签和特征分布的混合偏斜。为了解决这个问题,我们提出了一种联合学习框架 FL-Joint,它能利用辅助损失函数调整标签和特征分布。该框架采用类平衡分类器作为本地模型。它通过使用基于类条件信息和伪标签的辅助损失函数,在本地对齐标签和特征分布。这种对齐会促使客户特征分布向共享特征空间靠拢,从而完善决策边界并提高全局模型的泛化能力。在各种数据集和异构数据设置中进行的大量实验表明,与基线方法相比,我们的方法显著提高了准确性和收敛速度。
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
Complex & Intelligent Systems
Complex & Intelligent Systems COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
9.60
自引率
10.30%
发文量
297
期刊介绍: Complex & Intelligent Systems aims to provide a forum for presenting and discussing novel approaches, tools and techniques meant for attaining a cross-fertilization between the broad fields of complex systems, computational simulation, and intelligent analytics and visualization. The transdisciplinary research that the journal focuses on will expand the boundaries of our understanding by investigating the principles and processes that underlie many of the most profound problems facing society today.
×
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