An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee

TL;DR

This paper proposes a novel client selection scheme for federated learning that enhances efficiency and guarantees fairness, using Lyapunov optimization and a C2MAB-based estimation method, supported by theoretical and empirical results.

Contribution

It introduces a fairness-guaranteed client selection algorithm for federated learning based on Lyapunov optimization and C2MAB, with proven regret bounds and empirical validation.

Findings

The RBCS-F algorithm achieves bounded regret, ensuring fairness and efficiency.

Empirical results on public datasets validate the effectiveness of the proposed scheme.

The method improves training efficiency while maintaining fairness guarantees.

Abstract

The issue of potential privacy leakage during centralized AI's model training has drawn intensive concern from the public. A Parallel and Distributed Computing (or PDC) scheme, termed Federated Learning (FL), has emerged as a new paradigm to cope with the privacy issue by allowing clients to perform model training locally, without the necessity to upload their personal sensitive data. In FL, the number of clients could be sufficiently large, but the bandwidth available for model distribution and re-upload is quite limited, making it sensible to only involve part of the volunteers to participate in the training process. The client selection policy is critical to an FL process in terms of training efficiency, the final model's quality as well as fairness. In this paper, we will model the fairness guaranteed client selection as a Lyapunov optimization problem and then a C2MAB-based method is proposed for estimation of the model exchange time between each client and the server, based on which we design a fairness guaranteed algorithm termed RBCS-F for problem-solving. The regret of RBCS-F is strictly bounded by a finite constant, justifying its theoretical feasibility. Barring the theoretical results, more empirical data can be derived from our real training experiments on public datasets.