Timezone: »

Deep Structural Causal Models for Tractable Counterfactual Inference
Nick Pawlowski · Daniel Coelho de Castro · Ben Glocker

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #879

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.

Author Information

Nick Pawlowski (Imperial College London)
Daniel Coelho de Castro (Microsoft Research / Imperial College London)
Ben Glocker (Imperial College London)

More from the Same Authors