Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning

TL;DR

CondI introduces a federated learning framework using conditional diffusion models to explicitly impute missing data in multimodal clinical datasets, improving robustness and performance.

Contribution

It presents a novel two-phase training pipeline for explicit data imputation in federated learning with missing modalities, outperforming existing methods.

Findings

Achieves comparable results to state-of-the-art baselines on clinical datasets.

Explicit data imputation enhances model robustness against data incompleteness.

Utilizes conditional diffusion models for effective data recovery.

Abstract

Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative training, but real-world clinical applications often suffer from within-modality missingness caused by sensor intermittency or irregular sampling. Existing methods implicitly represent unobserved data via architectural alignment or missing embeddings, often failing to recover the true distribution and yielding sub-optimal performance. We propose CondI, a federated framework explicitly addressing this missingness using conditional diffusion models. CondI employs a two-phase training pipeline: first, imputing unobserved temporal components using available multimodal context and conditional embeddings; second, optimizing modality-specific extractors and joint embedding spaces. During inference, imputed raw data pass through trained extractors to generate robust features, providing a holistic representation for downstream tasks. Explicit data imputation ensures models operate on complete semantic structures, significantly enhancing resilience against severe data incompleteness. Experiments on three clinical datasets (PTB-XL, SLEEP-EDF, MIMIC-IV) demonstrate CondI achieves comparable results to state-of-the-art baselines. Code: https://github.com/ZhengWugeng/CondI