Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation

TL;DR

This paper introduces a deep learning framework that enables dynamic, end-to-end information sharing among treatment groups to improve individualized treatment effect estimation, especially in small observational datasets.

Contribution

It proposes a novel deep learning framework using soft weight sharing for end-to-end information sharing in ITE estimation, and introduces HyperITE learners that enhance existing methods.

Findings

Improves ITE estimation error across benchmarks.

More effective in smaller datasets.

Enhances existing ITE learners with HyperITE versions.

Abstract

Estimation of individualized treatment effects (ITE) from observational studies is a fundamental problem in causal inference and holds significant importance across domains, including healthcare. However, limited observational datasets pose challenges in reliable ITE estimation as data have to be split among treatment groups to train an ITE learner. While information sharing among treatment groups can partially alleviate the problem, there is currently no general framework for end-to-end information sharing in ITE estimation. To tackle this problem, we propose a deep learning framework based on `\textit{soft weight sharing}' to train ITE learners, enabling \textit{dynamic end-to-end} information sharing among treatment groups. The proposed framework complements existing ITE learners, and introduces a new class of ITE learners, referred to as \textit{HyperITE}. We extend state-of-the-art ITE learners with \textit{HyperITE} versions and evaluate them on IHDP, ACIC-2016, and Twins benchmarks. Our experimental results show that the proposed framework improves ITE estimation error, with increasing effectiveness for smaller datasets.