Semi-Asynchronous Federated Edge Learning Mechanism via Over-the-air Computation

TL;DR

This paper introduces PAOTA, a semi-asynchronous federated learning mechanism using over-the-air computation, which improves training efficiency and convergence in heterogeneous edge device environments.

Contribution

It proposes a novel semi-asynchronous aggregation method with AirComp that accounts for model staleness and divergence, optimizing uplink power to enhance FEEL performance.

Findings

Achieves convergence close to ideal Local SGD.

Reduces training time compared to synchronous FEEL.

Effective in heterogeneous device and data scenarios.

Abstract

Over-the-air Computation (AirComp) has been demonstrated as an effective transmission scheme to boost the efficiency of federated edge learning (FEEL). However, existing FEEL systems with AirComp scheme often employ traditional synchronous aggregation mechanisms for local model aggregation in each global round, which suffer from the stragglers issues. In this paper, we propose a semi-asynchronous aggregation FEEL mechanism with AirComp scheme (PAOTA) to improve the training efficiency of the FEEL system in the case of significant heterogeneity in data and devices. Taking the staleness and divergence of model updates from edge devices into consideration, we minimize the convergence upper bound of the FEEL global model by adjusting the uplink transmit power of edge devices at each aggregation period. The simulation results demonstrate that our proposed algorithm achieves convergence performance close to that of the ideal Local SGD. Furthermore, with the same target accuracy, the training time required for PAOTA is less than that of the ideal Local SGD and the synchronous FEEL algorithm via AirComp.