Characterization of the Global Bias Problem in Aerial Federated Learning
This addresses a critical issue for UAV-based federated learning systems by mitigating bias from channel uncertainties, though it is incremental as it builds on existing FL methods with a novel adaptation for aerial networks.
The paper tackles the global bias problem in aerial federated learning caused by unreliable wireless channels, which skews the model towards devices with better conditions, and proposes a channel-aware scheme that enforces equal contributions, demonstrating convergence and superiority on the MNIST dataset with specific parameter tuning to improve convergence rates.
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 paper characterizes the global bias problem of aerial FL in large-scale UAV networks. To this end, the paper 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.