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}.

翻译：在医学领域，联邦学习常处理高度不平衡的数据集，包括皮肤病变和胃肠道图像。现有的在高度不平衡数据集下的联邦方法主要关注优化全局模型，而未考虑因不同人群、发现结果和扫描仪而可能产生的医学影像类内变异。本文利用公开可用的自监督辅助网络研究跨客户端类内变异。具体而言，我们发现在每个客户端本地使用共享的辅助预训练模型（如MoCo-V2）能产生一致的散度度量。基于这些发现，我们推导出一种通过自监督先验的动态平衡模型聚合方法（MAS），以指导全局模型优化。Fed-MAS可与不同的本地学习方法结合使用，实现向高度鲁棒且无偏全局模型的有效模型聚合。我们的代码可在\url{https://github.com/xmed-lab/Fed-MAS}获取。