Deep Structural Causal Models for Tractable Counterfactual Inference
Pawlowski, Nick, Castro, Daniel C., Glocker, Ben
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.
Oct-22-2020
- Country:
- North America
- Greenland (0.04)
- United States > Massachusetts
- Middlesex County > Cambridge (0.04)
- Canada > British Columbia
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America
- Genre:
- Research Report (0.64)
- Industry:
- Health & Medicine
- Health Care Technology (1.00)
- Diagnostic Medicine > Imaging (0.87)
- Therapeutic Area (0.66)
- Health & Medicine
- Technology: