Fast Heterogeneous Federated Learning with Hybrid Client Selection
This work addresses communication efficiency and convergence speed in federated learning, which is important for distributed machine learning applications, but appears incremental as it builds on existing client selection methods.
The paper tackles slow convergence in federated learning caused by random client selection by proposing a clustering-based client selection scheme to reduce variance in model updates, achieving faster convergence with theoretical guarantees and experimental confirmation of superior efficiency.
Client selection schemes are widely adopted to handle the communication-efficient problems in recent studies of Federated Learning (FL). However, the large variance of the model updates aggregated from the randomly-selected unrepresentative subsets directly slows the FL convergence. We present a novel clustering-based client selection scheme to accelerate the FL convergence by variance reduction. Simple yet effective schemes are designed to improve the clustering effect and control the effect fluctuation, therefore, generating the client subset with certain representativeness of sampling. Theoretically, we demonstrate the improvement of the proposed scheme in variance reduction. We also present the tighter convergence guarantee of the proposed method thanks to the variance reduction. Experimental results confirm the exceed efficiency of our scheme compared to alternatives.