Causal Effect Estimation with Variational AutoEncoder and the Front Door Criterion

TL;DR

This paper introduces FDVAE, a deep generative model that uses variational autoencoders to learn representations for front-door adjustment, enabling causal effect estimation in the presence of unobserved confounders and mediators.

Contribution

It proposes a novel deep learning approach, FDVAE, to identify front-door adjustment sets from data without explicit search, improving causal inference with unobserved confounders.

Findings

FDVAE outperforms existing methods on synthetic datasets.

Performance is robust to unobserved confounder strength.

Method is effective despite dimensionality mismatches.

Abstract

An essential problem in causal inference is estimating causal effects from observational data. The problem becomes more challenging with the presence of unobserved confounders. When there are unobserved confounders, the commonly used back-door adjustment is not applicable. Although the instrumental variable (IV) methods can deal with unobserved confounders, they all assume that the treatment directly affects the outcome, and there is no mediator between the treatment and the outcome. This paper aims to use the front-door criterion to address the challenging problem with the presence of unobserved confounders and mediators. In practice, it is often difficult to identify the set of variables used for front-door adjustment from data. By leveraging the ability of deep generative models in representation learning, we propose FDVAE to learn the representation of a Front-Door adjustment set with a Variational AutoEncoder, instead of trying to search for a set of variables for front-door adjustment. Extensive experiments on synthetic datasets validate the effectiveness of FDVAE and its superiority over existing methods. The experiments also show that the performance of FDVAE is not sensitive to the causal strength of unobserved confounders and is feasible in the case of dimensionality mismatch between learned representations and the ground truth. We further apply the method to three real-world datasets to demonstrate its potential applications.