PA3Fed: Period-Aware Adaptive Aggregation for Improved Federated Learning

句号(音乐) 计算机科学 物理 声学
作者
Chunmei Huang,B. Liu
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence (AAAI)]
卷期号:39 (16): 17395-17403
标识
DOI:10.1609/aaai.v39i16.33912
摘要

Federated Learning (FL) is a distributed approach that enables collaborative model training while safeguarding client data privacy. Nevertheless, FL encounters difficulties due to statistical heterogeneity from the varied data distributions across numerous clients, which can affect overall efficiency and performance. Existing state-of-the-art FL methods often concentrate on optimizing interactions between clients, neglecting the potential insights from individual clients during training. Additionally, these approaches generally assume that every period of training has an equal impact on the final model's performance. To address these issues, this paper introduces a novel method, PA3Fed, which conducts period-aware adaptive aggregation for improved federated learning. The key idea is to identify the most critical periods, i.e., those with the highest information content and entropy, where we leverages each client's own performance variations during training for adaptive aggregation. Furthermore, because it operates independently of inter-client optimization approaches, it can be easily incorporated into other baselines for improved performance. Experimental results show that our method improves accuracy by up to 15% and significantly enhances stability.

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
zwhy完成签到 ,获得积分10
刚刚
甜蜜的楷瑞应助zyw采纳,获得10
1秒前
王华完成签到,获得积分20
1秒前
传奇3应助小新爱蜡笔采纳,获得10
1秒前
精明的甜瓜应助Noah采纳,获得10
2秒前
汉堡包应助莫问采纳,获得10
4秒前
asdlxz发布了新的文献求助10
4秒前
好运接收集成器完成签到,获得积分10
4秒前
Tina发布了新的文献求助10
5秒前
哈基米德应助ZeSir采纳,获得30
8秒前
14秒前
小学生发布了新的文献求助10
14秒前
15秒前
欢呼的未来完成签到 ,获得积分10
16秒前
烟花应助tuyoyo采纳,获得10
17秒前
莫问发布了新的文献求助10
18秒前
18秒前
我是老大应助小康学弟采纳,获得10
19秒前
江峰应助科研通管家采纳,获得10
19秒前
fang应助科研通管家采纳,获得10
19秒前
Owen应助科研通管家采纳,获得10
19秒前
SYLH应助科研通管家采纳,获得10
19秒前
小蘑菇应助科研通管家采纳,获得10
19秒前
HarryChan应助科研通管家采纳,获得10
19秒前
SYLH应助科研通管家采纳,获得20
19秒前
19秒前
19秒前
江峰应助科研通管家采纳,获得10
19秒前
SYLH应助科研通管家采纳,获得10
19秒前
研友_VZG7GZ应助科研通管家采纳,获得10
19秒前
Jasper应助科研通管家采纳,获得10
20秒前
元谷雪应助科研通管家采纳,获得10
20秒前
20秒前
江峰应助科研通管家采纳,获得10
20秒前
CAOHOU应助科研通管家采纳,获得10
20秒前
无花果应助科研通管家采纳,获得10
20秒前
江峰应助科研通管家采纳,获得10
20秒前
所所应助科研通管家采纳,获得10
20秒前
天天快乐应助科研通管家采纳,获得10
20秒前
打打应助科研通管家采纳,获得30
20秒前
高分求助中
【请各位用户详细阅读此贴后再求助】科研通的精品贴汇总(请勿应助) 10000
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 1000
Global Eyelash Assessment scale (GEA) 1000
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 4046142
求助须知:如何正确求助?哪些是违规求助? 3583869
关于积分的说明 11390815
捐赠科研通 3311163
什么是DOI,文献DOI怎么找? 1822153
邀请新用户注册赠送积分活动 894354
科研通“疑难数据库(出版商)”最低求助积分说明 816171