CAR-MFL: Cross-Modal Augmentation by Retrieval for Multimodal Federated Learning with Missing Modalities

TL;DR

This paper introduces CAR-MFL, a cross-modal retrieval-based data augmentation method for multimodal federated learning in healthcare, effectively handling missing modalities and enhancing performance while preserving privacy.

Contribution

It proposes a novel cross-modal augmentation technique using retrieval to fill missing modalities in federated learning, improving medical multimodal analysis.

Findings

Outperforms several baseline methods on medical multimodal benchmarks

Effectively handles missing modalities in federated learning scenarios

Ensures privacy preservation during model training

Abstract

Multimodal AI has demonstrated superior performance over unimodal approaches by leveraging diverse data sources for more comprehensive analysis. However, applying this effectiveness in healthcare is challenging due to the limited availability of public datasets. Federated learning presents an exciting solution, allowing the use of extensive databases from hospitals and health centers without centralizing sensitive data, thus maintaining privacy and security. Yet, research in multimodal federated learning, particularly in scenarios with missing modalities a common issue in healthcare datasets remains scarce, highlighting a critical area for future exploration. Toward this, we propose a novel method for multimodal federated learning with missing modalities. Our contribution lies in a novel cross-modal data augmentation by retrieval, leveraging the small publicly available dataset to fill the missing modalities in the clients. Our method learns the parameters in a federated manner, ensuring privacy protection and improving performance in multiple challenging multimodal benchmarks in the medical domain, surpassing several competitive baselines. Code Available: https://github.com/bhattarailab/CAR-MFL