DeceFL: A Principled Decentralized Federated Learning Framework

计算机科学 联合学习 趋同(经济学) 随机梯度下降算法 功能(生物学) 脆弱性(计算) 分布式计算 管道(软件) 人工智能 机器学习 计算机安全 进化生物学 人工神经网络 经济 生物 程序设计语言 经济增长
作者
Y. Yuan,Jun Li,Dou Jin,Zuogong Yue,Ruijuan Chen,Maolin Wang,Chen Sun,Lei Xu,Hao Feng,Xin He,Xinlei Yi,Tao Yang,Haitao Zhang,Shaochun Sui,Dawei Han
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2107.07171
摘要

Traditional machine learning relies on a centralized data pipeline, i.e., data are provided to a central server for model training. In many applications, however, data are inherently fragmented. Such a decentralized nature of these databases presents the biggest challenge for collaboration: sending all decentralized datasets to a central server raises serious privacy concerns. Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client. Here we propose a principled decentralized federated learning algorithm (DeceFL), which does not require a central client and relies only on local information transmission between clients and their neighbors, representing a fully decentralized learning framework. It has been further proven that every client reaches the global minimum with zero performance gap and achieves the same convergence rate $O(1/T)$ (where $T$ is the number of iterations in gradient descent) as centralized federated learning when the loss function is smooth and strongly convex. Finally, the proposed algorithm has been applied to a number of applications to illustrate its effectiveness for both convex and nonconvex loss functions, demonstrating its applicability to a wide range of real-world medical and industrial applications.
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
gao完成签到 ,获得积分10
1秒前
1秒前
joybee完成签到,获得积分0
1秒前
nieinei完成签到 ,获得积分10
2秒前
2秒前
上官翠花完成签到 ,获得积分10
3秒前
搞怪羊发布了新的文献求助10
7秒前
李爱国应助村里的山水采纳,获得10
7秒前
波里舞完成签到 ,获得积分10
7秒前
7秒前
wangjh发布了新的文献求助10
7秒前
科研通AI2S应助zxxx采纳,获得10
8秒前
科研通AI2S应助zxxx采纳,获得10
9秒前
cdercder应助zxxx采纳,获得10
9秒前
科研通AI2S应助zxxx采纳,获得10
9秒前
cdercder应助zxxx采纳,获得10
9秒前
10秒前
tdtk完成签到,获得积分10
11秒前
搞怪羊完成签到,获得积分10
12秒前
小爽完成签到,获得积分0
14秒前
小东子完成签到,获得积分20
14秒前
15秒前
某某完成签到 ,获得积分10
15秒前
SciGPT应助张建威采纳,获得10
15秒前
acadedog完成签到,获得积分10
16秒前
一株多肉完成签到,获得积分10
18秒前
ivy完成签到 ,获得积分10
18秒前
坚强的纸飞机完成签到,获得积分10
18秒前
恒河鲤完成签到,获得积分10
19秒前
acadedog发布了新的文献求助10
19秒前
hanhan完成签到 ,获得积分10
20秒前
程哲瀚完成签到,获得积分10
20秒前
20秒前
张张发布了新的文献求助10
21秒前
小东子发布了新的文献求助30
24秒前
24秒前
六斤发布了新的文献求助10
24秒前
汐颜完成签到,获得积分10
28秒前
bc应助安详的惜梦采纳,获得10
29秒前
30秒前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
ISCN 2024 – An International System for Human Cytogenomic Nomenclature (2024) 3000
Continuum Thermodynamics and Material Modelling 2000
Encyclopedia of Geology (2nd Edition) 2000
105th Edition CRC Handbook of Chemistry and Physics 1600
Maneuvering of a Damaged Navy Combatant 650
the MD Anderson Surgical Oncology Manual, Seventh Edition 300
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3777749
求助须知:如何正确求助?哪些是违规求助? 3323268
关于积分的说明 10213319
捐赠科研通 3038533
什么是DOI,文献DOI怎么找? 1667522
邀请新用户注册赠送积分活动 798139
科研通“疑难数据库(出版商)”最低求助积分说明 758275