Skip to main content Skip to main navigation


Relating Graph Neural Networks to Structural Causal Models

Matej Zecevic; Devendra Singh Dhami; Petar Velickovic; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2109.04173, Pages 0-10, arXiv, 2021.


Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations. For most processes of interest the underlying SCM will only be partially observable, thus causal inference tries leveraging the exposed. Graph neural networks (GNN) as universal approximators on structured input pose a viable candidate for causal learning, suggesting a tighter integration with SCM. To this effect we present a theoretical analysis from first principles that establishes a more general view on neural-causal models, revealing several novel connections between GNN and SCM. We establish a new model class for GNN-based causal inference that is necessary and sufficient for causal effect identification. Our empirical illustration on simulations and standard benchmarks validate our theoretical proofs.

Weitere Links