Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMO

TL;DR

This paper explores how cell-free massive MIMO can enhance over-the-air federated learning by reducing communication overhead and ensuring reliable convergence despite channel imperfections.

Contribution

It proposes a practical implementation of OTA-FL over cell-free massive MIMO considering channel correlation and imperfect CSI, with analytical and experimental convergence analysis.

Findings

Cell-free massive MIMO improves OTA-FL performance.

The proposed method converges reliably under realistic channel conditions.

Over-the-air computation reduces communication overhead in federated learning.

Abstract

Cell-free massive MIMO is emerging as a promising technology for future wireless communication systems, which is expected to offer uniform coverage and high spectral efficiency compared to classical cellular systems. We study in this paper how cell-free massive MIMO can support federated edge learning. Taking advantage of the additive nature of the wireless multiple access channel, over-the-air computation is exploited, where the clients send their local updates simultaneously over the same communication resource. This approach, known as over-the-air federated learning (OTA-FL), is proven to alleviate the communication overhead of federated learning over wireless networks. Considering channel correlation and only imperfect channel state information available at the central server, we propose a practical implementation of OTA-FL over cell-free massive MIMO. The convergence of the proposed implementation is studied analytically and experimentally, confirming the benefits of cell-free massive MIMO for OTA-FL.