Relating Graph Neural Networks to Structural Causal Models
Reviewed by Pithpith:QSIFYQJNopen to challenge →
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models
Smoothness assumptions on graphical model kernels produce Wasserstein estimation rates determined by local graph structure rather than ambient dimension.
-
Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem
Causal Process Models reframe dynamic causal graph discovery as multi-agent reinforcement learning to build sparse time-varying graphs only at active interactions, outperforming dense baselines on physical prediction.
-
DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs
DeepSWIP supplies exact single-world counterfactuals for DeepProbLog programs by neural materialization followed by SWIP transformation and quotient-WMC.
-
ERPPO: Entropy Regularization-based Proximal Policy Optimization
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.