A Meta-Learning Approach to Causal Inference

Dragos Cristian Manta, Philippe Brouillard, Dhanya Sridhar

Keywords: causal discovery, causal inference, meta-learning, amortized learning, adaptation, perturbation modeling

TL;DR: We introduce a novel method for predicting effects of interventions without learning a causal model

Abstract: Predicting the effect of unseen interventions is at the heart of many scientific endeavours. While causal discovery is often used to answer these causal questions, it involves learning a full causal model, not tailored to the specific goal of predicting unseen interventions, and operates under stringent assumptions. We introduce a novel method based on meta-learning that predicts interventional effects without explicitly assuming a causal model. Our preliminary results on synthetic data show that it can provide good generalization to unseen interventions, and it even compares favorably to a causal discovery method. Our model-agnostic method opens up many avenues for future exploration, particularly for settings where causal discovery cannot be applied.

Submission Number: 21