VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries

Abstract

In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making any parametric assumptions, VACA mimics the necessary properties of a Structural Causal Model (SCM) to provide a flexible and practical framework for approximating interventions (do-operator) and abduction-action-prediction steps. As a result, and as shown by our empirical results, VACA accurately approximates the interventional and counterfactual distributions on diverse SCMs. Finally, we apply VACA to evaluate counterfactual fairness in fair classification problems, as well as to learn fair classifiers without compromising performance.

References in corpus (6)

• Variational Graph Auto-Encoders
• ETA Prediction with Graph Neural Networks in Google Maps
• DAG-GNN: DAG Structure Learning with Graph Neural Networks
• Relating Graph Neural Networks to Structural Causal Models
• Causal Inference with Deep Causal Graphs
• Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder