Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification

--Asynchronous Federated Learning (AFL) enables distributed model training across multiple mobile devices, allowing each device to independently update its local model without waiting for others. However, device mobility introduces intermittent connectivity, which necessitates gradient sparsification and leads to model staleness, jointly affecting AFL convergence. This paper develops a theoretical model to characterize the interplay among sparsification, model staleness and mobility-induced contact patterns, and their joint impact on AFL convergence. Based on the analysis, we propose a mobility-aware dynamic sparsification (MADS) algorithm that optimizes the sparsification degree based on contact time and model staleness. Closed-form solutions are derived, showing that under low-speed conditions, MADS increases the sparsification degree to enhance convergence, while under high-speed conditions, it reduces the sparsification degree to guarantee reliable uploads within limited contact time. Compared with the state-of-the-art benchmarks, the MADS algorithm increases the image classification accuracy on the CIF AR-10 dataset by 8 . The advent of 6G networks promises to support a wide range of new applications, including autonomous driving, smart cities, and the internet of things [1], [2]. These applications generate massive data and require efficient training of machine learning (ML) models [3]. Traditional centralized ML introduces privacy concerns and high latency. With increasingly powerful edge devices such as mobile phones, smart vehicles, and IoT sensors, it becomes feasible to shift the ML training process from centralized servers to these edge devices themselves.