A Fair Federated Learning Framework With Reinforcement Learning

TL;DR

This paper introduces PG-FFL, a reinforcement learning-based framework for federated learning that dynamically assigns client weights to improve fairness, convergence speed, and overall performance.

Contribution

It proposes a novel RL framework that automatically learns client aggregation weights and uses Gini coefficient for fairness in federated learning.

Findings

Outperforms baseline methods in accuracy and fairness

Speeds up convergence in diverse datasets

Enhances fairness across heterogeneous clients

Abstract

Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. However, heterogeneous data distributions over different clients remain a challenge to mainstream FL algorithms, which may cause slow convergence, overall performance degradation and unfairness of performance across clients. To address these problems, in this study we propose a reinforcement learning framework, called PG-FFL, which automatically learns a policy to assign aggregation weights to clients. Additionally, we propose to utilize Gini coefficient as the measure of fairness for FL. More importantly, we apply the Gini coefficient and validation accuracy of clients in each communication round to construct a reward function for the reinforcement learning. Our PG-FFL is also compatible to many existing FL algorithms. We conduct extensive experiments over diverse datasets to verify the effectiveness of our framework. The experimental results show that our framework can outperform baseline methods in terms of overall performance, fairness and convergence speed.