亲爱的研友该休息了!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,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Addressing Class Imbalance in Federated Learning

作者
Lixu Wang,Shichao Xu,Xiao Wang,Qi Zhu
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence]
卷期号:35 (11): 10165-10173 被引量:274
标识
DOI:10.1609/aaai.v35i11.17219
摘要

Federated learning (FL) is a promising approach for training decentralized data located on local client devices while improving efficiency and privacy. However, the distribution and quantity of the training data on the clients' side may lead to significant challenges such as class imbalance and non-IID (non-independent and identically distributed) data, which could greatly impact the performance of the common model. While much effort has been devoted to helping FL models converge when encountering non-IID data, the imbalance issue has not been sufficiently addressed. In particular, as FL training is executed by exchanging gradients in an encrypted form, the training data is not completely observable to either clients or server, and previous methods for class imbalance do not perform well for FL. Therefore, it is crucial to design new methods for detecting class imbalance in FL and mitigating its impact. In this work, we propose a monitoring scheme that can infer the composition of training data for each FL round, and design a new loss function -- Ratio Loss to mitigate the impact of the imbalance. Our experiments demonstrate the importance of acknowledging class imbalance and taking measures as early as possible in FL training, and the effectiveness of our method in mitigating the impact. Our method is shown to significantly outperform previous methods, while maintaining client privacy.
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
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
JEK发布了新的文献求助10
刚刚
1秒前
1秒前
5秒前
6秒前
科研通AI6.4的应助被小羊采纳,获得10
7秒前
斯文芷巧发布了新的文献求助10
7秒前
8秒前
9秒前
10秒前
10秒前
10秒前
嘻嘻哈哈的应助被科研通管家采纳,获得10
12秒前
李健的应助被科研通管家采纳,获得10
12秒前
上岸的风的应助被科研通管家采纳,获得20
12秒前
fantasy的应助被科研通管家采纳,获得10
12秒前
小马甲的应助被科研通管家采纳,获得10
12秒前
13秒前
13秒前
vnewgnl的应助被科研通管家采纳,获得10
13秒前
上官若男的应助被科研通管家采纳,获得10
13秒前
Hello的应助被科研通管家采纳,获得10
13秒前
13秒前
null的应助被科研通管家采纳,获得20
13秒前
fantasy的应助被科研通管家采纳,获得10
13秒前
14秒前
14秒前
14秒前
阿腾发布了新的文献求助10
14秒前
吴yx完成签到,获得积分10
16秒前
16秒前
今后的应助被爱科研的小羊采纳,获得10
17秒前
简单的曼青完成签到,获得积分10
18秒前
18秒前
18秒前
21秒前
清爽晓博发布了新的文献求助10
21秒前
24秒前
27秒前
27秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
Grapes 1000
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8179717
求助须知:如何正确求助?哪些是违规求助? 9569938
关于积分的说明 21807807
捐赠科研通 7775242
什么是DOI,文献DOI怎么找? 3433072
关于科研通互助平台的介绍 2557044
邀请新用户注册赠送积分活动 2478783