Federated Learning for Time-Series Healthcare Sensing with Incomplete Modalities

TL;DR

This paper introduces FLISM, an efficient federated learning algorithm designed for multimodal healthcare time-series data with incomplete modalities, improving accuracy and efficiency over existing methods.

Contribution

FLISM is a novel federated learning approach that effectively handles incomplete modalities using modality-invariant learning, quality-aware aggregation, and knowledge distillation.

Findings

Achieves high accuracy on real-world healthcare datasets.

Faster and more efficient than state-of-the-art methods.

Effectively manages diverse and incomplete modality data.

Abstract

Many healthcare sensing applications utilize multimodal time-series data from sensors embedded in mobile and wearable devices. Federated Learning (FL), with its privacy-preserving advantages, is particularly well-suited for health applications. However, most multimodal FL methods assume the availability of complete modality data for local training, which is often unrealistic. Moreover, recent approaches tackling incomplete modalities scale poorly and become inefficient as the number of modalities increases. To address these limitations, we propose FLISM, an efficient FL training algorithm with incomplete sensing modalities while maintaining high accuracy. FLISM employs three key techniques: (1) modality-invariant representation learning to extract effective features from clients with a diverse set of modalities, (2) modality quality-aware aggregation to prioritize contributions from clients with higher-quality modality data, and (3) global-aligned knowledge distillation to reduce local update shifts caused by modality differences. Extensive experiments on real-world datasets show that FLISM not only achieves high accuracy but is also faster and more efficient compared with state-of-the-art methods handling incomplete modality problems in FL. We release the code as open-source at https://github.com/AdibaOrz/FLISM.