A New Perspective to Boost Performance Fairness for Medical Federated Learning
This work addresses fairness issues in medical federated learning for hospitals, but it is incremental as it builds on existing fair FL methods by incorporating domain shift considerations.
The paper tackled performance fairness in medical federated learning by addressing domain shift, proposing Fed-LWR to dynamically weight hospitals based on feature representation differences, resulting in better and fairer performance on medical image segmentation benchmarks.
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.