Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification
This work addresses the challenge of data imbalance and variability in federated learning for medical imaging, which is incremental as it builds on existing methods by incorporating self-supervised priors.
The paper tackles the problem of federated learning with highly imbalanced medical image datasets by addressing inter-client intra-class variations, resulting in a method called Fed-MAS that achieves a robust and unbiased global model.
In the medical field, federated learning commonly deals with highly imbalanced datasets, including skin lesions and gastrointestinal images. Existing federated methods under highly imbalanced datasets primarily focus on optimizing a global model without incorporating the intra-class variations that can arise in medical imaging due to different populations, findings, and scanners. In this paper, we study the inter-client intra-class variations with publicly available self-supervised auxiliary networks. Specifically, we find that employing a shared auxiliary pre-trained model, like MoCo-V2, locally on every client yields consistent divergence measurements. Based on these findings, we derive a dynamic balanced model aggregation via self-supervised priors (MAS) to guide the global model optimization. Fed-MAS can be utilized with different local learning methods for effective model aggregation toward a highly robust and unbiased global model. Our code is available at \url{https://github.com/xmed-lab/Fed-MAS}.