Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimization
This addresses a fundamental challenge in causal inference for applications like user growth in internet companies, offering an incremental improvement over existing disentangled representation methods.
The paper tackles the problem of learning independent disentangled factors for individual-level treatment effect estimation, proposing a method that uses mutual information minimization to ensure factor independence and achieves superior performance on benchmarks and real-world datasets.
Learning individual-level treatment effect is a fundamental problem in causal inference and has received increasing attention in many areas, especially in the user growth area which concerns many internet companies. Recently, disentangled representation learning methods that decompose covariates into three latent factors, including instrumental, confounding and adjustment factors, have witnessed great success in treatment effect estimation. However, it remains an open problem how to learn the underlying disentangled factors precisely. Specifically, previous methods fail to obtain independent disentangled factors, which is a necessary condition for identifying treatment effect. In this paper, we propose Disentangled Representations for Counterfactual Regression via Mutual Information Minimization (MIM-DRCFR), which uses a multi-task learning framework to share information when learning the latent factors and incorporates MI minimization learning criteria to ensure the independence of these factors. Extensive experiments including public benchmarks and real-world industrial user growth datasets demonstrate that our method performs much better than state-of-the-art methods.