Parameter-less Asynchronous Federated Learning under Computation and Communication Constraints
Mengfan Wu, Mate Boban, Falko Dressler · 2023
Federated Learning is a fast-developing distributed learning scheme that has promising applications in vertical domains such as industrial automation and connected automated driving. In this paper we address the heterogeneity of the participation of devices in federated learning caused by: i) non-uniform distribution of local data; ii) uneven and varying computational resources across the devices; and iii) dynamic communication link. We propose a quasi-dynamic simulation scheme allowing realistic approximation of these three factors of heterogeneity. Aggregation schemes at the server based on the clients’ work status are implemented. We show that the new asynchronous aggregation algorithm does not require tuning of hyper-parameters such as the round time in synchronous federated learning and the aggregation weight in classic asynchronous aggregation, while providing better or comparable performance in terms of accuracy and convergence speed.