Adversarial De-confounding in Individualised Treatment Effects Estimation
This work addresses the fundamental issue of confounding in observational studies for personalized treatment effects, which is crucial for fields like healthcare and policy-making, though it appears incremental as it builds on existing adversarial and representation learning techniques.
The paper tackled the problem of de-confounding in individualized treatment effects estimation from observational data by using disentangled representations with adversarial training to balance confounders, resulting in improved state-of-the-art methods with lower error rates on synthetic and real-world datasets.
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.