Abstract:There is a growing interest in estimating heterogeneous treatment effects across individuals using their high-dimensional feature attributes. Achieving high performance in such high-dimensional heterogeneous treatment effect estimation is challenging because in this setup, it is usual that some features induce sample selection bias while others do not but are predictive of potential outcomes. To avoid losing such predictive feature information, existing methods learn separate feature representations using the inverse of probability weighting (IPW). However, due to the numerically unstable IPW weights, they suffer from estimation bias under a finite sample setup. To develop a numerically robust estimator via weighted representation learning, we propose a differentiable Pareto-smoothed weighting framework that replaces extreme weight values in an end-to-end fashion. Experimental results show that by effectively correcting the weight values, our method outperforms the existing ones, including traditional weighting schemes.