Adversarial De-confounding in Individualised Treatment Effects Estimation

TL;DR

This paper introduces an adversarial de-confounding method using disentangled representations to improve individualised treatment effect estimation in observational studies, effectively balancing confounders and reducing estimation errors.

Contribution

It proposes a novel adversarial training approach with disentangled representations to selectively balance confounders for better ITE estimation in binary treatment settings.

Findings

Improves state-of-the-art ITE estimation accuracy

Effective on synthetic and real-world datasets

Handles varying degrees of confounding

Abstract

Observational studies have recently received significant attention from the machine learning community due to the increasingly available non-experimental observational data and the limitations of the experimental studies, such as considerable cost, impracticality, small and less representative sample sizes, etc. In observational studies, de-confounding is a fundamental problem of individualised treatment effects (ITE) estimation. This paper proposes disentangled representations with adversarial training to selectively balance the confounders in the binary treatment setting for the ITE estimation. The adversarial training of treatment policy selectively encourages treatment-agnostic balanced representations for the confounders and helps to estimate the ITE in the observational studies via counterfactual inference. Empirical results on synthetic and real-world datasets, with varying degrees of confounding, prove that our proposed approach improves the state-of-the-art methods in achieving lower error in the ITE estimation.