Characterization of the Global Bias Problem in Aerial Federated Learning

Abstract

Unmanned aerial vehicles (UAVs) mobility enables flexible and customized federated learning (FL) at the network edge. However, the underlying uncertainties in the aerial-terrestrial wireless channel may lead to a biased FL model. In particular, the distribution of the global model and the aggregation of the local updates within the FL learning rounds at the UAVs are governed by the reliability of the wireless channel. This creates an undesirable bias towards the training data of ground devices with better channel conditions, and vice versa. This letter characterizes the global bias problem of aerial FL in large-scale UAV networks. To this end, this letter proposes a channel-aware distribution and aggregation scheme to enforce equal contribution from all devices in the FL training as a means to resolve the global bias problem. We demonstrate the convergence of the proposed method by experimenting with the MNIST dataset and show its superiority compared to existing methods. The obtained results enable system parameter tuning to relieve the impact of the aerial channel deficiency on the FL convergence rate.

More by Ruslan Zhagypar

• LyRA-FL: A Scheduler for Federated Fine-Tuning of Foundation Models in Wireless NetworksIEEE Transactions on Mobile Computing · 2026
• Clustering and Aggregation for Wireless Federated Learning Under Label-Flipping AttacksIEEE Wireless Communications Letters · 2026
• UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence AnalysisIEEE Transactions on Machine Learning in Communications and Networking · 2025 · Citations: 22
• Communication-Aware Optimizers for FedMeta Learning in Aerial Wireless NetworksIEEE Wireless Communications Letters · 2024