Asynchronous Federated Learning with Incentive Mechanism Based on Contract Theory

TL;DR

This paper introduces an asynchronous federated learning framework with an incentive mechanism based on contract theory, improving accuracy and efficiency while addressing client heterogeneity and straggler issues.

Contribution

It proposes a novel asynchronous FL framework integrating an incentive mechanism that adaptively adjusts client training epochs considering delay and accuracy.

Findings

Test accuracy improved by 3.12% over FedAvg.

Achieved 5.84% higher accuracy than FedProx without attacks.

Reduced computation time for same accuracy target.

Abstract

To address the challenges posed by the heterogeneity inherent in federated learning (FL) and to attract high-quality clients, various incentive mechanisms have been employed. However, existing incentive mechanisms are typically utilized in conventional synchronous aggregation, resulting in significant straggler issues. In this study, we propose a novel asynchronous FL framework that integrates an incentive mechanism based on contract theory. Within the incentive mechanism, we strive to maximize the utility of the task publisher by adaptively adjusting clients' local model training epochs, taking into account factors such as time delay and test accuracy. In the asynchronous scheme, considering client quality, we devise aggregation weights and an access control algorithm to facilitate asynchronous aggregation. Through experiments conducted on the MNIST dataset, the simulation results demonstrate that the test accuracy achieved by our framework is 3.12% and 5.84% higher than that achieved by FedAvg and FedProx without any attacks, respectively. The framework exhibits a 1.35% accuracy improvement over the ideal Local SGD under attacks. Furthermore, aiming for the same target accuracy, our framework demands notably less computation time than both FedAvg and FedProx.