Adaptive Test-Time Personalization for Federated Learning

作者
Wenxuan Bao,Tianxin Wei,Haohan Wang,Jingrui He
出处
期刊: [Neural Information Processing Systems Foundation]
卷期号:: 77882-77914 被引量:10
标识
DOI:10.52202/075280-3403
摘要

Personalized federated learning algorithms have shown promising results in adapting models to various distribution shifts. However, most of these methods require labeled data on testing clients for personalization, which is usually unavailable in real-world scenarios. In this paper, we introduce a novel setting called test-time personalized federated learning (TTPFL), where clients locally adapt a global model in an unsupervised way without relying on any labeled data during test-time. While traditional test-time adaptation (TTA) can be used in this scenario, most of them inherently assume training data come from a single domain, while they come from multiple clients (source domains) with different distributions. Overlooking these domain interrelationships can result in suboptimal generalization. Moreover, most TTA algorithms are designed for a specific kind of distribution shift and lack the flexibility to handle multiple kinds of distribution shifts in FL. In this paper, we find that this lack of flexibility partially results from their pre-defining which modules to adapt in the model. To tackle this challenge, we propose a novel algorithm called ATP to adaptively learns the adaptation rates for each module in the model from distribution shifts among source domains. Theoretical analysis proves the strong generalization of ATP. Extensive experiments demonstrate its superiority in handling various distribution shifts including label shift, image corruptions, and domain shift, outperforming existing TTA methods across multiple datasets and model architectures. Our code is available at https://github.com/baowenxuan/ATP .

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
刚刚
小豆芽芽完成签到,获得积分10
刚刚
刚刚
1秒前
常常完成签到,获得积分10
1秒前
成江完成签到,获得积分10
1秒前
1秒前
丘比特的应助被小螃蟹大大王采纳,获得10
1秒前
2秒前
温暖的问候完成签到,获得积分10
3秒前
老登发布了新的文献求助10
3秒前
默默完成签到 ,获得积分10
4秒前
巴豆醇完成签到,获得积分10
4秒前
李博宇发布了新的文献求助10
5秒前
小鹿发布了新的文献求助10
5秒前
chonghuang完成签到,获得积分10
5秒前
月神樂发布了新的文献求助10
5秒前
5秒前
风笛发布了新的文献求助10
5秒前
凡人烦事发布了新的文献求助10
5秒前
5秒前
Maestro_S的应助被心情不错采纳,获得10
5秒前
march的应助被qianzhihe采纳,获得10
6秒前
6秒前
Lv完成签到,获得积分10
6秒前
6秒前
7秒前
7秒前
wangjiayi完成签到 ,获得积分20
7秒前
阿白发布了新的文献求助10
7秒前
7秒前
8秒前
Samsara完成签到 ,获得积分10
8秒前
末位牛马完成签到,获得积分10
8秒前
半山完成签到,获得积分10
8秒前
豆豆发布了新的文献求助10
8秒前
极限001的应助被wangzong采纳,获得30
9秒前
9秒前
虚心的雁玉完成签到,获得积分10
9秒前
犹豫白柏发布了新的文献求助10
9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
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
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
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 8181279
求助须知:如何正确求助?哪些是违规求助? 9571198
关于积分的说明 21817073
捐赠科研通 7777612
什么是DOI,文献DOI怎么找? 3433454
关于科研通互助平台的介绍 2557692
邀请新用户注册赠送积分活动 2479519