Communication Efficient Federated Learning with Linear Convergence on Heterogeneous Data
This addresses communication bottlenecks in distributed learning for applications with non-IID data, though it is incremental as it builds on existing methods like NIDS.
The paper tackles the client-drift problem in federated learning on heterogeneous data by proposing FedCET, which ensures linear convergence to the exact solution while reducing communication overhead by sharing only one variable instead of two.
By letting local clients perform multiple local updates before communicating with a parameter server, modern federated learning algorithms such as FedAvg tackle the communication bottleneck problem in distributed learning and have found many successful applications. However, this asynchrony between local updates and communication also leads to a ''client-drift'' problem when the data is heterogeneous (not independent and identically distributed), resulting in errors in the final learning result. In this paper, we propose a federated learning algorithm, which is called FedCET, to ensure accurate convergence even under heterogeneous distributions of data across clients. Inspired by the distributed optimization algorithm NIDS, we use learning rates to weight information received from local clients to eliminate the ''client-drift''. We prove that under appropriate learning rates, FedCET can ensure linear convergence to the exact solution. Different from existing algorithms which have to share both gradients and a drift-correction term to ensure accurate convergence under heterogeneous data distributions, FedCET only shares one variable, which significantly reduces communication overhead. Numerical comparison with existing counterpart algorithms confirms the effectiveness of FedCET.