A New Perspective to Boost Performance Fairness for Medical Federated Learning

TL;DR

This paper introduces Fed-LWR, a novel federated learning approach for medical applications that addresses domain shift by dynamically weighting hospitals based on feature divergence, leading to fairer and improved performance.

Contribution

Fed-LWR is the first method to explicitly address feature shift in medical federated learning by dynamically estimating and compensating for domain differences among hospitals.

Findings

Outperforms existing fair FL methods on medical image segmentation benchmarks.

Achieves more equitable performance across hospitals with diverse data.

Effectively mitigates domain shift impacts in medical federated learning.

Abstract

Improving the fairness of federated learning (FL) benefits healthy and sustainable collaboration, especially for medical applications. However, existing fair FL methods ignore the specific characteristics of medical FL applications, i.e., domain shift among the datasets from different hospitals. In this work, we propose Fed-LWR to improve performance fairness from the perspective of feature shift, a key issue influencing the performance of medical FL systems caused by domain shift. Specifically, we dynamically perceive the bias of the global model across all hospitals by estimating the layer-wise difference in feature representations between local and global models. To minimize global divergence, we assign higher weights to hospitals with larger differences. The estimated client weights help us to re-aggregate the local models per layer to obtain a fairer global model. We evaluate our method on two widely used federated medical image segmentation benchmarks. The results demonstrate that our method achieves better and fairer performance compared with several state-of-the-art fair FL methods.