Using decentralized data for federated training is one promising emerging research direction for alleviating data scarcity in the medical domain. However, in contrast to large-scale fully labeled data commonly seen in general object recognition tasks, the local medical datasets are more likely to only have images annotated for a subset of classes of interest due to high annotation costs. In this paper, we consider a practical yet under-explored problem, where underrepresented classes only have few labeled instances available and only exist in a few clients of the federated system. We show that standard federated learning approaches fail to learn robust multi-label classifiers with extreme class imbalance and address it by proposing a novel federated learning framework, FedFew. FedFew consists of three stages, where the first stage leverages federated self-supervised learning to learn class-agnostic representations. In the second stage, the decentralized partially labeled data are exploited to learn an energy-based multi-label classifier for the common classes. Finally, the underrepresented classes are detected based on the energy and a prototype-based nearest-neighbor model is proposed for few-shot matching. We evaluate FedFew on multi-label thoracic disease classification tasks and demonstrate that it outperforms the federated baselines by a large margin.

‍