How Does Cell-Free Massive MIMO Support Multiple Federated Learning Groups?

TL;DR

This paper explores how cell-free massive MIMO networks can efficiently support multiple federated learning groups simultaneously, proposing novel asynchronous execution and resource allocation schemes to enhance stability and reduce iteration time.

Contribution

It introduces a new framework using cell-free massive MIMO for supporting multiple FL groups, with asynchronous execution and an optimal resource allocation algorithm.

Findings

Supports multiple FL groups with stable operation

Proposes asynchronous FL iteration scheme

Develops low-complexity resource allocation algorithm

Abstract

Federated learning (FL) has been considered as a promising learning framework for future machine learning systems due to its privacy preservation and communication efficiency. In beyond-5G/6G systems, it is likely to have multiple FL groups with different learning purposes. This scenario leads to a question: How does a wireless network support multiple FL groups? As an answer, we first propose to use a cell-free massive multiple-input multiple-output (MIMO) network to guarantee the stable operation of multiple FL processes by letting the iterations of these FL processes be executed together within a large-scale coherence time. We then develop a novel scheme that asynchronously executes the iterations of FL processes under multicasting downlink and conventional uplink transmission protocols. Finally, we propose a simple/low-complexity resource allocation algorithm which optimally chooses the power and computation resources to minimize the execution time of each iteration of each FL process.