<ul><li>Asynchronous Federated Learning (AFL) allows model training on multiple mobile devices independently.</li><li>Device mobility leads to intermittent connectivity, requiring gradient sparsification and causing model staleness.</li><li>A theoretical model is developed to analyze the impact of sparsification, model staleness, and mobility on AFL convergence.</li><li>A mobility-aware dynamic sparsification (MADS) algorithm is proposed to optimize sparsification based on contact time and model staleness, improving convergence and achieving better results in experiments.</li></ul>

Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification

Discover more