TEMPO: IMPROVING TRAINING PERFORMANCE IN CROSS-SILO FEDERATED LEARNING

Different from its commonly studied scenario to centrally store clients' data in institutions, which implicitly neglects clients' data privacy, we study cross-silo federated learning in a preferable setting to keep private data on clients, and train the global model with a three-layer structure, where the institutions aggregate model updates from their clients for several rounds before sending their aggregated updates to the central server. In this context, we mathematically prove that the number of clients' local training epochs affects the global model performance and thus propose a new approach, Tempo, to adaptively tune the epoch number of each client through training. The results of our evaluation conducted under real network environments show that Tempo can not only improve training performance in terms of global model accuracy and communication efficiency, but also the elapsed training time.