VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
arXiv:2110.14690
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 (13)
- Auto-Encoding Variational Bayes
- Neural Message Passing for Quantum Chemistry
- Variational Graph Auto-Encoders
- Counterfactual Fairness
- Causal Effect Inference with Deep Latent-Variable Models
- ETA Prediction with Graph Neural Networks in Google Maps
- DAG-GNN: DAG Structure Learning with Graph Neural Networks
- Causality for Machine Learning
- Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks
- Relating Graph Neural Networks to Structural Causal Models
- Explaining Visual Models by Causal Attribution
- Causal Inference with Deep Causal Graphs
- Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder