Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning

TL;DR

This paper introduces an over-the-air aggregation method for wireless federated learning that trains multiple models simultaneously, improving convergence speed and efficiency over traditional single-model approaches.

Contribution

It develops a joint beamforming optimization framework for multi-model over-the-air aggregation, with a low-complexity solution to enhance federated learning performance.

Findings

Multi-model FL with OAA outperforms sequential training.

The proposed method achieves faster convergence.

Simulation results validate the effectiveness of the approach.

Abstract

We propose an uplink over-the-air aggregation (OAA) method for wireless federated learning (FL) that simultaneously trains multiple models. To maximize the multi-model training convergence rate, we derive an upper bound on the optimality gap of the global model update, and then, formulate an uplink joint transmit-receive beamforming optimization problem to minimize this upper bound. We solve this problem using the block coordinate descent approach, which admits low-complexity closed-form updates. Simulation results show that our proposed multi-model FL with fast OAA substantially outperforms sequentially training multiple models under the conventional single-model approach.