Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxies
This work addresses the challenge of leveraging unstructured data for causal inference, which is incremental as it builds on existing methods by incorporating multi-modal proxies.
The paper tackled the problem of estimating causal effects from observational data when confounders are unobserved but unstructured data like images and text are available as proxies, and introduced a deep multi-modal structural equations model that outperformed existing methods in tasks such as genomics and healthcare.
Estimating the effect of intervention from observational data while accounting for confounding variables is a key task in causal inference. Oftentimes, the confounders are unobserved, but we have access to large amounts of additional unstructured data (images, text) that contain valuable proxy signal about the missing confounders. This paper argues that leveraging this unstructured data can greatly improve the accuracy of causal effect estimation. Specifically, we introduce deep multi-modal structural equations, a generative model for causal effect estimation in which confounders are latent variables and unstructured data are proxy variables. This model supports multiple multi-modal proxies (images, text) as well as missing data. We empirically demonstrate that our approach outperforms existing methods based on propensity scores and corrects for confounding using unstructured inputs on tasks in genomics and healthcare. Our methods can potentially support the use of large amounts of data that were previously not used in causal inference