Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization

doi:10.1109/TWC.2023.3288122

	Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization
	Yuanming Shi1 ; Shuhao Xia1 ; Yong Zhou1 ; Yijie Mao1 ; Chunxiao Jiang 2; Meixia Tao 3
	2023
发表期刊	IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
ISSN	1536-1276
EISSN	1558-2248
卷号	PP 期号:99 页码:1-1
发表状态	已发表
DOI	10.1109/TWC.2023.3288122
摘要	Vertical federated learning (FL) is a collaborative machine learning framework that enables devices to learn a global model from the feature-partition datasets without sharing local raw data. However, as the number of the local intermediate outputs is proportional to the training samples, it is critical to develop communication-efficient techniques for wireless vertical FL to support high-dimensional model aggregation with full device participation. In this paper, we propose a novel cloud radio access network (Cloud-RAN) based vertical FL system to enable fast and accurate model aggregation by leveraging over-the-air computation (AirComp) and alleviating communication straggler issue with cooperative model aggregation among geographically distributed edge servers. However, the model aggregation error caused by AirComp and quantization errors caused by the limited fronthaul capacity degrade the learning performance for vertical FL. To address these issues, we characterize the convergence behavior of the vertical FL algorithm considering both uplink and downlink transmissions. To improve the learning performance, we establish a system optimization framework by joint transceiver and fronthaul quantization design, for which successive convex approximation and alternate convex search based system optimization algorithms are developed. We conduct extensive simulations to demonstrate the effectiveness of the proposed system architecture and optimization framework for vertical FL. IEEE
关键词	Cooperative communication Distributed computer systems Learning systems Radio access networks Radio transceivers Atmospheric modeling Cloud radio access network Computational modelling Optimisations Over the airs Over-the-air computation Radio access networks System optimizations Vertical federated learning Wireless communications
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20232714336808
EI主题词	Approximation algorithms
EI分类号	716.3 Radio Systems and Equipment ; 722.3 Data Communication, Equipment and Techniques ; 722.4 Digital Computers and Systems ; 921 Mathematics
原始文献类型	Article in Press
来源库	IEEE
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/316845
专题	信息科学与技术学院信息科学与技术学院_PI研究组_石远明组信息科学与技术学院_PI研究组_周勇组信息科学与技术学院_博士生信息科学与技术学院_PI研究组_毛奕婕组
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.Tsinghua Space Center and the Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China 3.Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Yuanming Shi,Shuhao Xia,Yong Zhou,et al. Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization[J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,2023,PP(99):1-1.
APA	Yuanming Shi,Shuhao Xia,Yong Zhou,Yijie Mao,Chunxiao Jiang,&Meixia Tao.(2023).Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization.IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,PP(99),1-1.
MLA	Yuanming Shi,et al."Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization".IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS PP.99(2023):1-1.