ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
For multimodal federated learning in medical imaging, ProMoE-FL provides a robust solution to missing modalities without needing public datasets, showing consistent improvements over existing methods.
ProMoE-FL addresses multimodal federated learning with missing modalities by using a prototype-conditioned mixture of experts to synthesize missing features, outperforming state-of-the-art methods on four chest X-ray datasets in both homogeneous and heterogeneous settings.
In this paper, we address the problem of multimodal federated learning with missing modality. Existing methods utilize an additional public dataset or perform naive feature synthesis that is based solely on the available modality. To address these limitations, we propose ProMoE-FL, a Prototype-conditioned Mixture-of-Experts framework for robust missing-modality feature synthesis in multimodal federated learning. ProMoE-FL builds a global client-aware prototype bank that captures clinically meaningful modality priors across institutions. Our Mixture of Experts is conditioned on these prototypes and modality indices to enable direction-aware expert routing for dynamically synthesizing missing features. We perform extensive quantitative and qualitative evaluations on four public chest X-ray datasets (MIMIC-CXR, NIH Open-I, PadChest, and CheXpert) and demonstrate that ProMoE-FL consistently outperforms state-of-the-art methods in both homogeneous as well as the more challenging heterogeneous settings.