Targeted VAE: Structured Inference and Targeted Learning for Causal Parameter Estimation

Matthew James Vowels, Necati Cihan Camgoz, Richard Bowden

Keywords: causal inference, variational inference, disentanglement, variational autoencoder

Abstract: Undertaking causal inference with observational data is extremely useful across a wide range of domains including the development of medical treatments, advertisements and marketing, and policy making. There are two main challenges associated with undertaking causal inference using observational data: treatment assignment heterogeneity (i.e., differences between the treated and untreated groups), and an absence of counterfactual data (i.e., not knowing what would have happened if an individual who did get treatment, were instead to have not been treated). We address these two challenges by combining structured inference and targeted learning. To our knowledge, Targeted Variational AutoEncoder (TVAE) is the first method to incorporate targeted learning into deep latent variable models. Results demonstrate competitive and state of the art performance.

One-sentence Summary: TVAE combines targeted learning theory with amortized variational inference to learn structured latent encodings to yield treatment effect estimation.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=-7RVDlAmnP