Enhancing Fairness in Federated Learning: A Contribution‐Based Differentiated Model Approach
Tao Wan, Xianqing Deng, Weichuan Liao, Nan Jiang · International Journal of Intelligent Systems · 2023
Federated learning (FL) has emerged as a promising framework for collaborative machine learning, allowing the training of machine learning models on distributed devices without centralizing sensitive data. However, FL falls short in terms of fairness, as each client receives the same model regardless of their individual contributions. This unfairness discourages active client participation in FL. To address this challenge, we propose a contribution‐based differentiated global model mechanism. Specifically, we introduce the contribution score as a metric to assess client contributions in FL and utilize deep Q‐networks (DQN) to dynamically update the contribution scores. Subsequently, we allocate clients to different clusters based on their contributions by using a clustering algorithm, where each cluster is associated with a distinct global model. This mechanism encourages clients to make greater contributions for improved global models. Experimental results confirm the effectiveness of our approach in enhancing fairness in FL.