Deep Structural Causal Models for Tractable Counterfactual Inference

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 miss...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Pawlowski, Nick, Castro, Daniel C, Glocker, Ben
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 22.10.2020
Subjects
Causation
Computer Science - Learning
Datasets
Inference
Machine learning
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary: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. The code for all our experiments is available at https://github.com/biomedia-mira/deepscm.
ISSN:2331-8422
DOI:10.48550/arxiv.2006.06485