Anchor Sampling for Federated Learning with Partial Client Participation

TL;DR

This paper introduces FedAMD, a federated learning framework using anchor sampling to improve training efficiency and accuracy under partial client participation, addressing data heterogeneity and communication costs.

Contribution

The paper proposes a novel anchor sampling method in FedAMD that separates clients into anchor and miner groups, enhancing convergence and performance in partial participation scenarios.

Findings

Achieves up to O(1/ε) fewer communication rounds for convergence.

Significantly reduces computation and communication costs.

Improves test accuracy compared to state-of-the-art methods.

Abstract

Compared with full client participation, partial client participation is a more practical scenario in federated learning, but it may amplify some challenges in federated learning, such as data heterogeneity. The lack of inactive clients' updates in partial client participation makes it more likely for the model aggregation to deviate from the aggregation based on full client participation. Training with large batches on individual clients is proposed to address data heterogeneity in general, but their effectiveness under partial client participation is not clear. Motivated by these challenges, we propose to develop a novel federated learning framework, referred to as FedAMD, for partial client participation. The core idea is anchor sampling, which separates partial participants into anchor and miner groups. Each client in the anchor group aims at the local bullseye with the gradient computation using a large batch. Guided by the bullseyes, clients in the miner group steer multiple near-optimal local updates using small batches and update the global model. By integrating the results of the two groups, FedAMD is able to accelerate the training process and improve the model performance. Measured by $\epsilon$-approximation and compared to the state-of-the-art methods, FedAMD achieves the convergence by up to $O(1/\epsilon)$ fewer communication rounds under non-convex objectives. Empirical studies on real-world datasets validate the effectiveness of FedAMD and demonstrate the superiority of the proposed algorithm: Not only does it considerably save computation and communication costs, but also the test accuracy significantly improves.