Variational Causal Autoencoder for Interventional and Counterfactual Queries

no code implementations • NeurIPS 2021 • Pablo Sanchez Martin, Miriam Rateike, Isabel Valera

We propose the Variational Causal Autoencoder (VCAUSE), 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.

Causal Inference counterfactual +1