Federated Learning via Over-the-Air Computation

doi:10.1109/TWC.2019.2961673

	Federated Learning via Over-the-Air Computation
	Kai Yang1 ; Tao Jiang1 ; Yuanming Shi1 ; Zhi Ding 2
	2020-03
发表期刊	IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
ISSN	1558-2248
卷号	PP 期号:99 页码:1
发表状态	已发表
DOI	10.1109/TWC.2019.2961673
摘要	The stringent requirements for low-latency and privacy of the emerging high-stake applications with intelligent devices such as drones and smart vehicles make the cloud computing inapplicable in these scenarios. Instead, edge machine learning becomes increasingly attractive for performing training and inference directly at network edges without sending data to a centralized data center. This stimulates a nascent field termed as federated learning for training a machine learning model on computation, storage, energy and bandwidth limited mobile devices in a distributed manner. To preserve data privacy and address the issues of unbalanced and non-IID data points across different devices, the federated averaging algorithm has been proposed for global model aggregation by computing the weighted average of locally updated model at each selected device. However, the limited communication bandwidth becomes the main bottleneck for aggregating the locally computed updates. We thus propose a novel over-the-air computation based approach for fast global model aggregation via exploring the superposition property of a wireless multiple-access channel. This is achieved by joint device selection and beamforming design, which is modeled as a sparse and low-rank optimization problem to support efficient algorithms design. To achieve this goal, we provide a difference-of-convex-functions (DC) representation for the sparse and low-rank function to enhance sparsity and accurately detect the fixed-rank constraint in the procedure of device selection. A DC algorithm is further developed to solve the resulting DC program with global convergence guarantees. The algorithmic advantages and admirable performance of the proposed methodologies are demonstrated through extensive numerical results.
关键词	Federated learning over-the-air computation edge machine learning sparse optimization low-rank optimization difference-of-convex-functions DC programming
URL	查看原文
收录类别	SCI ; SCIE ; EI
语种	英语
WOS研究方向	Engineering ; Telecommunications
WOS类目	Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000521186100040
EI入藏号	20201208319512
EI主题词	Bandwidth ; Data privacy ; Functions ; Machine learning
EI分类号	Information Theory and Signal Processing:716.1 ; Data Storage, Equipment and Techniques:722.1 ; Mathematics:921
原始文献类型	Journal article (JA)
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/49989
专题	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_石远明组信息科学与技术学院_硕士生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.Department of Electrical and Computer Engineering, University of California at Davis, Davis, USA
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	Kai Yang,Tao Jiang,Yuanming Shi,et al. Federated Learning via Over-the-Air Computation[J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,2020,PP(99):1.
APA	Kai Yang,Tao Jiang,Yuanming Shi,&Zhi Ding.(2020).Federated Learning via Over-the-Air Computation.IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,PP(99),1.
MLA	Kai Yang,et al."Federated Learning via Over-the-Air Computation".IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS PP.99(2020):1.