Federated Learning in Heterogeneous Cloud Computing Environment

Abstract

This study examines key characteristics of cloud computing technology within the domain of federated learning, with the primary objective of exploring the principles concerning distributed computing acceleration ratio and storage input/output efficiency across various network segments. Combining the heterogeneous characteristics of cloud segments, we present a novel approach for distributed model training strategies by using the federated learning technique. This approach can keep the accuracy of the model, enhance training efficiency, and protect user privacy. The experiment demonstrates that the proposed strategy outperforms the baseline method, which does not account for variations in different segments.