Ground-Assisted Federated Learning in LEO Satellite Constellations

In Low Earth Orbit (LEO) mega constellations, there are relevant use cases, such as inference based on satellite imaging, in which a large number of satellites collaboratively train machine learning model without sharing their local datasets. To address this problem, we propose new set algorithms Federated (FL), including novel asynchronous FL procedure FedAvg that exhibits better robustness against heterogeneous scenarios than the state-of-the-art. Extensive numerical evaluations MNIST and CIFAR-10 datasets highlight fast convergence speed excellent asymptotic test accuracy proposed method.