{
  "id": "2006.06485",
  "version": "v1",
  "published": "2020-06-11T14:52:08.000Z",
  "updated": "2020-06-11T14:52:08.000Z",
  "title": "Deep Structural Causal Models for Tractable Counterfactual Inference",
  "authors": [
    "Nick Pawlowski",
    "Daniel C. Castro",
    "Ben Glocker"
  ],
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "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. The code for all our experiments is available at https://github.com/biomedia-mira/deepscm.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-06-11T14:52:08.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep structural causal models",
      "tractable counterfactual inference",
      "synthetic dataset built",
      "building structural causal models",
      "existing deep causal learning methods"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}