Causal Representation Learning from Multimodal Biomedical Observations

TL;DR

This paper introduces a flexible causal representation learning framework for multimodal biomedical data, providing theoretical guarantees and practical methods to identify interpretable causal variables, validated on synthetic and real-world datasets.

Contribution

It develops nonparametric identification conditions for multimodal data with causal relationships, extending subspace identification and emphasizing structural sparsity in biomedical systems.

Findings

Theoretical guarantees for latent causal variable identifiability.

Effective framework demonstrated on synthetic and real datasets.

Results align with established biomedical knowledge.

Abstract

Prevalent in biomedical applications (e.g., human phenotype research), multimodal datasets can provide valuable insights into the underlying physiological mechanisms. However, current machine learning (ML) models designed to analyze these datasets often lack interpretability and identifiability guarantees, which are essential for biomedical research. Recent advances in causal representation learning have shown promise in identifying interpretable latent causal variables with formal theoretical guarantees. Unfortunately, most current work on multimodal distributions either relies on restrictive parametric assumptions or yields only coarse identification results, limiting their applicability to biomedical research that favors a detailed understanding of the mechanisms. In this work, we aim to develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biomedical datasets. Theoretically, we consider a nonparametric latent distribution (c.f., parametric assumptions in previous work) that allows for causal relationships across potentially different modalities. We establish identifiability guarantees for each latent component, extending the subspace identification results from previous work. Our key theoretical contribution is the structural sparsity of causal connections between modalities, which, as we will discuss, is natural for a large collection of biomedical systems. Empirically, we present a practical framework to instantiate our theoretical insights. We demonstrate the effectiveness of our approach through extensive experiments on both numerical and synthetic datasets. Results on a real-world human phenotype dataset are consistent with established biomedical research, validating our theoretical and methodological framework.