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

Hans Jarett Ong, Yoichi Chikahara, Tomoharu Iwata
10/25/2025
stat.MLcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

86% match2025

A Meta-Reinforcement Learning Algorithm for Causal Discovery

85% match1 repo122022

A Meta-Learning Approach to Bayesian Causal Discovery

84% match2024

Adaptive Online Experimental Design for Causal Discovery

82% match1 repo62024

Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization

82% match2025

Interventional Causal Structure Discovery over Graphical Models with Convergence and Optimality Guarantees

81% match2024

Cite this paper

@article{ong2025metacadi,
  title  = {MetaCaDI: A Meta-Learning Framework for Scalable Causal Discovery with Unknown Interventions},
  author = {Hans Jarett Ong and Yoichi Chikahara and Tomoharu Iwata},
  year   = {2025},
  eprint = {2510.22298},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.22298v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.22298.svg)](https://codeofpaper.com/paper/2510.22298)

Discussion