Wireless Federated Learning over MIMO Networks: Joint Device Scheduling and Beamforming Design

TL;DR

This paper proposes a joint device scheduling and beamforming strategy for wireless federated learning over MIMO networks, aiming to improve convergence and efficiency in 6G AI services.

Contribution

It introduces a novel approach combining device scheduling and beamforming design, with theoretical convergence analysis and optimization under latency and power constraints.

Findings

Theoretical convergence analysis of wireless FL over MIMO networks.

Optimized device scheduling improves FL performance under resource constraints.

Numerical results confirm the effectiveness of the proposed approach.

Abstract

Federated learning (FL) is recognized as a key enabling technology to support distributed artificial intelligence (AI) services in future 6G. By supporting decentralized data training and collaborative model training among devices, FL inherently tames privacy leakage and reduces transmission costs. Whereas, the performance of the wireless FL is typically restricted by the communication latency. Multiple-input multiple-output (MIMO) technique is one promising solution to build up a communication-efficient edge FL system with limited radio resources. In this paper, we propose a novel joint device scheduling and receive beamforming design approach to reduce the FL convergence gap over shared wireless MIMO networks. Specifically, we theoretically establish the convergence analysis of the FL process, and then apply the proposed device scheduling policy to maximize the number of weighted devices under the FL system latency and sum power constraints. Numerical results verify the theoretical analysis of the FL convergence and exhibit the appealing learning performance of the proposed approach.