Estimating Individual Treatment Effects with Structure Maintained Representation Learning

Music City Center 

Recent advances in causal inference have shifted the focus from estimating average treatment effects to individual treatment effects (ITE). We propose a novel Structure Maintained Representation Learning (SMRL) approach to improve ITE estimation by preserving the correlation between baseline covariates and their learned representations. Our method introduces a discriminator to balance distributional alignment and information retention, minimizing an upper bound on treatment estimation error. We demonstrate SMRL's superiority over existing methods through extensive experiments on both simulated and real-world datasets, including EHR data from the MIMIC-III database.

causal inference