Federated Learning with Server Learning: Enhancing Performance for Non-IID Data
This addresses a key bottleneck in Federated Learning for distributed systems with heterogeneous data, though it is an incremental enhancement to existing methods.
The paper tackles performance degradation in Federated Learning with non-IID client data by enabling the server to learn from a small auxiliary dataset, resulting in significant improvements in model accuracy and convergence time.
Federated Learning (FL) has emerged as a means of distributed learning using local data stored at clients with a coordinating server. Recent studies showed that FL can suffer from poor performance and slower convergence when training data at clients are not independent and identically distributed. Here we consider a new complementary approach to mitigating this performance degradation by allowing the server to perform auxiliary learning from a small dataset. Our analysis and experiments show that this new approach can achieve significant improvements in both model accuracy and convergence time even when the server dataset is small and its distribution differs from that of the aggregated data from all clients.