Learning Neural Causal Models with Active Interventions

Nino Scherrer, Olexa Bilaniuk, Yashas Annadani, Anirudh Goyal, Patrick Schwab, Bernhard Schölkopf, Michael Curtis Mozer, Yoshua Bengio, Stefan Bauer, Nan Rosemary Ke

Keywords: neural causal discovery, causal structure learning, active learning, experimental design

Abstract: Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science. The appealing scaling properties of neural networks have recently led to a surge of interest in differentiable neural network-based methods for learning causal structures from data. So far, differentiable causal discovery has focused on static datasets of observational or interventional origin. In this work, we introduce an active intervention-targeting mechanism which enables quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting and is applicable for both discrete and continuous optimization formulations of learning the underlying directed acyclic graph (DAG) from data. We examine the proposed method across multiple frameworks in a wide range of settings and demonstrate superior performance on multiple benchmarks from simulated to real-world data.

One-sentence Summary: We propose an active intervention-targeting mechanism which enables quick identification of the underlying causal structure in differentiable causal discovery.

Community Implementations: [ 6 code implementations](https://www.catalyzex.com/paper/arxiv:2109.02429/code)