Contrastive Individual Treatment Effects Estimation.

Inferring causal effects on observational data has been widely adopted in various fields. One of the cornerstones of causal inference research, named Individual Treatment Effects (ITE) estimation, aims to predict the expected difference between the treatment and control outcome. It provides a more precise solution to meeting personalized needs while enhancing prediction accuracy in machine learning tasks. Nevertheless, the lack of counterfactual truth and selection bias remain the main challenges in ITE estimation and exert detrimental effects on inference accuracy. In this work, we propose a novel Contrastive Individual Treatment Effects (CITE) estimation framework to alleviate both above issues. Based on the contrastive task designed for causal inference, we fully exploit the self-supervision information hidden in data to achieve balanced and predictive representations while appropriately leveraging causal prior knowledge. Our method outperforms the state-of-the-art ITE estimation algorithms on several real-world and semi-synthetic datasets, which validates its efficacy and superiority.