Maverick-Aware Shapley Valuation for Client Selection in Federated Learning

TL;DR

This paper introduces a novel Maverick-aware Shapley valuation and client selection method for federated learning, improving fairness and model performance by accounting for clients with rare data classes.

Contribution

The paper proposes a class-wise Shapley valuation and a client selection mechanism called FedMS that enhances fairness and effectiveness in federated learning with data heterogeneity.

Findings

FedMS outperforms baselines in model accuracy.

Fairer Shapley reward distribution achieved.

Improved handling of Mavericks in FL systems.

Abstract

Federated Learning (FL) allows clients to train a model collaboratively without sharing their private data. One key challenge in practical FL systems is data heterogeneity, particularly in handling clients with rare data, also referred to as Mavericks. These clients own one or more data classes exclusively, and the model performance becomes poor without their participation. Thus, utilizing Mavericks throughout training is crucial. In this paper, we first design a Maverick-aware Shapley valuation that fairly evaluates the contribution of Mavericks. The main idea is to compute the clients' Shapley values (SV) class-wise, i.e., per label. Next, we propose FedMS, a Maverick-Shapley client selection mechanism for FL that intelligently selects the clients that contribute the most in each round, by employing our Maverick-aware SV-based contribution score. We show that, compared to an extensive list of baselines, FedMS achieves better model performance and fairer Shapley Rewards distribution.