Deep Structural Causal Models for Tractable Counterfactual Inference
Nick Pawlowski, Daniel Coelho de Castro, Ben Glocker
Abstract
We formulate a general framework for building structural causal models (SCMs) with deep learning components. The proposed approach employs normalising flows and variational inference to enable tractable inference of exogenous noise variables - a crucial step for counterfactual inference that is missing from existing deep causal learning methods. Our framework is validated on a synthetic dataset built on MNIST as well as on a real-world medical dataset of brain MRI scans. Our experimental results indicate that we can successfully train deep SCMs that are capable of all three levels of Pearl's ladder of causation: association, intervention, and counterfactuals, giving rise to a powerful new approach for answering causal questions in imaging applications and beyond.
BibTeX
@inproceedings{NEURIPS2020_0987b8b3,
author = {Pawlowski, Nick and Coelho de Castro, Daniel and Glocker, Ben},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {857--869},
publisher = {Curran Associates, Inc.},
title = {Deep Structural Causal Models for Tractable Counterfactual Inference},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/0987b8b338d6c90bbedd8631bc499221-Paper.pdf},
volume = {33},
year = {2020}
}