English

Dynamic Fair Federated Learning Based on Reinforcement Learning

Machine Learning 2023-11-03 v1 Computers and Society Information Theory math.IT

Abstract

Federated learning enables a collaborative training and optimization of global models among a group of devices without sharing local data samples. However, the heterogeneity of data in federated learning can lead to unfair representation of the global model across different devices. To address the fairness issue in federated learning, we propose a dynamic q fairness federated learning algorithm with reinforcement learning, called DQFFL. DQFFL aims to mitigate the discrepancies in device aggregation and enhance the fairness of treatment for all groups involved in federated learning. To quantify fairness, DQFFL leverages the performance of the global federated model on each device and incorporates {\alpha}-fairness to transform the preservation of fairness during federated aggregation into the distribution of client weights in the aggregation process. Considering the sensitivity of parameters in measuring fairness, we propose to utilize reinforcement learning for dynamic parameters during aggregation. Experimental results demonstrate that our DQFFL outperforms the state-of-the-art methods in terms of overall performance, fairness and convergence speed.

Keywords

Cite

@article{arxiv.2311.00959,
  title  = {Dynamic Fair Federated Learning Based on Reinforcement Learning},
  author = {Weikang Chen and Junping Du and Yingxia Shao and Jia Wang and Yangxi Zhou},
  journal= {arXiv preprint arXiv:2311.00959},
  year   = {2023}
}
R2 v1 2026-06-28T13:09:14.707Z