Causal Effect Variational Autoencoder with Uniform Treatment
This work addresses covariate shift issues in causal inference for deep learning, offering an incremental improvement over existing methods like CEVAE.
The paper tackles the problem of distribution shift in causal effect estimation by introducing UTVAE, which uses uniform treatment distribution during training to mitigate this shift, resulting in lower absolute average treatment effect error and better precision in heterogeneous effect estimation compared to CEVAE on synthetic and IHDP datasets.
Domain adaptation and covariate shift are big issues in deep learning and they ultimately affect any causal inference algorithms that rely on deep neural networks. Causal effect variational autoencoder (CEVAE) is trained to predict the outcome given observational treatment data and it suffers from the distribution shift at test time. In this paper, we introduce uniform treatment variational autoencoders (UTVAE) that are trained with uniform treatment distribution using importance sampling and show that using uniform treatment over observational treatment distribution leads to better causal inference by mitigating the distribution shift that occurs from training to test time. We also explore the combination of uniform and observational treatment distributions with inference and generative network training objectives to find a better training procedure for inferring treatment effects. Experimentally, we find that the proposed UTVAE yields better absolute average treatment effect error and precision in the estimation of heterogeneous effect error than the CEVAE on synthetic and IHDP datasets.