FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning
This addresses communication inefficiencies in federated learning for privacy-preserving collaborative training, but it is incremental as it builds on existing methods like FedSTS and FedSampling.
The paper tackles the problem of inefficient client sampling in federated learning by proposing FedSTaS, a method that stratifies clients based on compressed gradients and uses optimal allocation and data sampling. Experiments on three datasets show it achieves higher accuracy than FedSTS within fixed training rounds.
Federated learning (FL) is a machine learning methodology that involves the collaborative training of a global model across multiple decentralized clients in a privacy-preserving way. Several FL methods are introduced to tackle communication inefficiencies but do not address how to sample participating clients in each round effectively and in a privacy-preserving manner. In this paper, we propose \textit{FedSTaS}, a client and data-level sampling method inspired by \textit{FedSTS} and \textit{FedSampling}. In each federated learning round, \textit{FedSTaS} stratifies clients based on their compressed gradients, re-allocate the number of clients to sample using an optimal Neyman allocation, and sample local data from each participating clients using a data uniform sampling strategy. Experiments on three datasets show that \textit{FedSTaS} can achieve higher accuracy scores than those of \textit{FedSTS} within a fixed number of training rounds.