FedSS: Federated Learning with Smart Selection of clients
This addresses bias and inefficiency in federated learning for privacy-preserving distributed systems, but appears incremental as it builds on existing client selection methods.
The paper tackles bias in federated learning client selection, which discriminates against slow clients, by proposing smart selection and scheduling techniques to balance fast convergence and heterogeneity.
Federated learning provides the ability to learn over heterogeneous user data in a distributed manner while preserving user privacy. However, its current client selection technique is a source of bias as it discriminates against slow clients. For starters, it selects clients that satisfy certain network and system-specific criteria, thus not selecting slow clients. Even when such clients are included in the training process, they either struggle with the training or are dropped altogether for being too slow. Our proposed idea looks to find a sweet spot between fast convergence and heterogeneity by looking at smart client selection and scheduling techniques.