UAV-Assisted Hierarchical Aggregation for Over-the-Air Federated Learning

TL;DR

This paper introduces a UAV-assisted hierarchical aggregation scheme for over-the-air federated learning, reducing communication costs and addressing straggler issues through UAV-based gradient aggregation and trajectory optimization.

Contribution

It proposes a novel UAV-assisted hierarchical aggregation framework and develops an optimization algorithm for UAV trajectory and aggregation coefficients.

Findings

Significant reduction in communication costs.

Effective mitigation of straggler effects.

Improved federated learning performance with UAV assistance.

Abstract

With huge amounts of data explosively increasing in the mobile edge, over-the-air federated learning (OA-FL) emerges as a promising technique to reduce communication costs and privacy leak risks. However, when devices in a relatively large area cooperatively train a machine learning model, the attendant straggler issues will significantly reduce the learning performance. In this paper, we propose an unmanned aerial vehicle (UAV) assisted OA-FL system, where the UAV acts as a parameter server (PS) to aggregate the local gradients hierarchically for global model updating. Under this UAV-assisted hierarchical aggregation scheme, we carry out a gradient-correlation-aware FL performance analysis. We then formulate a mean squared error (MSE) minimization problem to tune the UAV trajectory and the global aggregation coefficients based on the analysis results. An algorithm based on alternating optimization (AO) and successive convex approximation (SCA) is developed to solve the formulated problem. Simulation results demonstrate the great potential of our UAV-assisted hierarchical aggregation scheme.