Massive MIMO for Serving Federated Learning and Non-Federated Learning Users

TL;DR

This paper explores the use of massive MIMO technology with half-duplex and full-duplex schemes to efficiently serve both federated learning and non-FL users in future wireless networks, optimizing rates under latency constraints.

Contribution

It introduces novel HD and FD communication schemes with power control algorithms for joint FL and non-FL user service in massive MIMO systems, addressing uplink and downlink challenges.

Findings

FD scheme outperforms HD when self-interference is low or moderate.

Proposed algorithms significantly outperform baseline schemes.

Massive MIMO effectively supports joint FL and non-FL user communication.

Abstract

With its privacy preservation and communication efficiency, federated learning (FL) has emerged as a promising learning framework for beyond 5G wireless networks. It is anticipated that future wireless networks will jointly serve both FL and downlink non-FL user groups in the same time-frequency resource. While in the downlink of each FL iteration, both groups jointly receive data from the base station in the same time-frequency resource, the uplink of each FL iteration requires bidirectional communication to support uplink transmission for FL users and downlink transmission for non-FL users. To overcome this challenge, we present half-duplex (HD) and full-duplex (FD) communication schemes to serve both groups. More specifically, we adopt the massive multiple-input multiple-output technology and aim to maximize the minimum effective rate of non-FL users under a quality of service (QoS) latency constraint for FL users. Since the formulated problem is highly nonconvex, we propose a power control algorithm based on successive convex approximation to find a stationary solution. Numerical results show that the proposed solutions perform significantly better than the considered baselines schemes. Moreover, the FD-based scheme outperforms the HD-based scheme in scenarios where the self-interference is small or moderate and/or the size of FL model updates is large.