VACA: Designing Variational Graph Autoencoders for Causal Queries

Authors

  • Pablo Sánchez-Martin Max Planck Institute for Intelligent Systems, Tübingen, Germany Department of Computer Science of Saarland University, Saarbrücken, Germany
  • Miriam Rateike Max Planck Institute for Intelligent Systems, Tübingen, Germany Department of Computer Science of Saarland University, Saarbrücken, Germany
  • Isabel Valera Department of Computer Science of Saarland University, Saarbrücken, Germany

DOI:

https://doi.org/10.1609/aaai.v36i7.20789

Keywords:

Machine Learning (ML)

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.

Downloads

Published

2022-06-28

How to Cite

Sánchez-Martin, P., Rateike, M., & Valera, I. (2022). VACA: Designing Variational Graph Autoencoders for Causal Queries. Proceedings of the AAAI Conference on Artificial Intelligence, 36(7), 8159-8168. https://doi.org/10.1609/aaai.v36i7.20789

Issue

Section

AAAI Technical Track on Machine Learning II