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

TL;DR

VACA introduces a flexible variational graph autoencoder framework for causal inference that accurately models interventional and counterfactual distributions without hidden confounders, enabling fair classification.

Contribution

It is the first to develop a non-parametric variational autoencoder approach for causal inference on graphs, handling interventions and counterfactuals without hidden confounders.

Findings

VACA accurately approximates interventional distributions across diverse SCMs.

VACA effectively models counterfactual distributions for causal inference.

Application of VACA to fair classification demonstrates improved fairness without performance loss.

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.