MetaCaDI: A Meta-Learning Framework for Scalable Causal Discovery with Unknown Interventions

TL;DR

MetaCaDI is a novel meta-learning framework that efficiently uncovers causal structures and unknown interventions in complex systems, especially effective with limited data, by leveraging a Bayesian approach with analytical adaptation.

Contribution

It introduces the first meta-learning approach for joint causal discovery and intervention prediction, using a Bayesian model with closed-form adaptation to improve efficiency and robustness.

Findings

Outperforms state-of-the-art methods on synthetic and gene expression data.

Accurately recovers causal graphs and intervention targets with as few as 10 data points.

Demonstrates robustness in data-scarce scenarios.

Abstract

Uncovering the underlying causal mechanisms of complex real-world systems remains a significant challenge, as these systems often entail high data collection costs and involve unknown interventions. We introduce MetaCaDI, the first framework to cast the joint discovery of a causal graph and unknown interventions as a meta-learning problem. MetaCaDI is a Bayesian framework that learns a shared causal graph structure across multiple experiments and is optimized to rapidly adapt to new, few-shot intervention target prediction tasks. A key innovation is our model's analytical adaptation, which uses a closed-form solution to bypass expensive and potentially unstable gradient-based bilevel optimization. Extensive experiments on synthetic and complex gene expression data demonstrate that MetaCaDI significantly outperforms state-of-the-art methods. It excels at both causal graph recovery and identifying intervention targets from as few as 10 data instances, proving its robustness in data-scarce scenarios.