Deep Structural Causal Models for Tractable Counterfactual Inference

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.

arXiv commentAccepted to NeurIPS 2020

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Categorical Reparameterization with Gumbel-Softmax
• Variational Inference with Normalizing Flows
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Counterfactual Fairness
• Deep Convolutional Inverse Graphics Network
• Adversarially Learned Inference
• Causal Effect Inference with Deep Latent-Variable Models
• Composing graphical models with neural networks for structured representations and fast inference
• Causality for Machine Learning
• Learning Independent Causal Mechanisms
• CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
• Learning to synthesise the ageing brain without longitudinal data
• Learning Likelihoods with Conditional Normalizing Flows
• Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models
• Conditional Density Estimation with Bayesian Normalising Flows
• Graphical Generative Adversarial Networks
• Variational Message Passing with Structured Inference Networks
• CausalVAE: Structured Causal Disentanglement in Variational Autoencoder

Cited by in corpus (15)

• Learning Disentangled Representations in the Imaging Domain
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• Learning to synthesise the ageing brain without longitudinal data
• medigan: a Python library of pretrained generative models for medical image synthesis
• Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph
• Relating Graph Neural Networks to Structural Causal Models
• FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging
• 3D Brain and Heart Volume Generative Models: A Survey
• A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Models
• Harmonization with Flow-based Causal Inference
• Estimation of Counterfactual Interventions under Uncertainties
• Causal Autoregressive Flows
• Blood Glucose Control Via Pre-trained Counterfactual Invertible Neural Networks
• Adaptation and Generalization for Unknown Sensitive Factors of Variations
• Quantifying intrinsic causal contributions via structure preserving interventions