A Weighted Average Consensus Approach for Decentralized Federated Learning

doi:10.1007/s11633-022-1338-z

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	A Weighted Average Consensus Approach for Decentralized Federated Learning
	Alessandro Giuseppi 1
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2022
卷号	19 页码:319-330
摘要	Federated learning (FedL) is a machine learning (ML) technique utilized to train deep neural networks (DeepNNs) in a distributed way without the need to share data among the federated training clients. FedL was proposed for edge computing and Internet of things (IoT) tasks in which a centralized server was responsible for coordinating and governing the training process. To remove the design limitation implied by the centralized entity, this work proposes two different solutions to decentralize existing FedL algorithms, enabling the application of FedL on networks with arbitrary communication topologies, and thus extending the domain of application of FedL to more complex scenarios and new tasks. Of the two proposed algorithms, one, called FedLCon, is developed based on results from discrete-time weighted average consensus theory and is able to reconstruct the performances of the standard centralized FedL solutions, as also shown by the reported validation tests.
关键词	Federated learning (FedL) deep learning federated averaging (FedAvg) machine learning (ML) artificial intelligence discrete-time consensus distributed systems
DOI	10.1007/s11633-022-1338-z
引用统计	被引频次：9[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/49645
专题	学术期刊_Machine Intelligence Research
作者单位	1.Department of Computer, Control, and Management Engineering, University of Rome La Sapienza, Rome 00185, Italy 2.Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples 80125, Italy
推荐引用方式 GB/T 7714	Alessandro Giuseppi. A Weighted Average Consensus Approach for Decentralized Federated Learning[J]. Machine Intelligence Research,2022,19:319-330.
APA	Alessandro Giuseppi.(2022).A Weighted Average Consensus Approach for Decentralized Federated Learning.Machine Intelligence Research,19,319-330.
MLA	Alessandro Giuseppi."A Weighted Average Consensus Approach for Decentralized Federated Learning".Machine Intelligence Research 19(2022):319-330.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-02-053.pdf（1462KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载