A Stochastic Gradient Approach for Communication Efficient Confederated Learning
Bin Wang, Jun Fang, Hongbin Li, Yonina C. Eldar · 2024
In this work, we consider a multi-server federated learning (FL) framework, referred to as Confederated Learning (CFL), in order to accommodate a larger number of users. To reduce the communication overhead of the CFL system, we propose a linearly convergent stochastic gradient method. The proposed algorithm incorporates a conditionally-triggered user selection (CTUS) mechanism as the central component. Simulation results show that it achieves advantageous communication efficiency over GT-SAGA.