Deep Structural Causal Models for Tractable Counterfactual Inference

2020/06/11 by Nick Pawlowski, Pawlowski, Nick, Daniel C. Castro +3 · 18 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.2006.06485

openalex publication_date 2020/06/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Auto-Encoding Variational Bayes
• Ageing and the brain
• Gradient-based learning applied to document recognition
• Composing graphical models with neural networks for structured representations and fast inference
• Categorical Reparameterization with Gumbel-Softmax
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• CausalVAE: Structured Causal Disentanglement in Variational Autoencoder

Cited by

• Unifying Causal Reinforcement Learning: Survey, Taxonomy, Algorithms and Applications
• Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representation
• Cyclic Counterfactuals under Shift-Scale Interventions
• Towards Error-Centric Intelligence II: Energy-Structured Causal Models
• Counterfactual Identifiability via Dynamic Optimal Transport
• Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoders
• Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis
• Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
• GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes
• Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
• Diffusion-Based Data Augmentation for Medical Image Segmentation
• DoubleGen: Debiased Generative Modeling of Counterfactuals
• Relating Graph Neural Networks to Structural Causal Models
• Integrating Anatomical Priors into a Causal Diffusion Model
• RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcuts
• Synthetic Counterfactual Labels for Efficient Conformal Counterfactual Inference
• See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
• Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation

Related

• High Fidelity Image Counterfactuals with Probabilistic Causal Models
• Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges
• Harmonization with Flow-based Causal Inference
• Diffusion Causal Models for Counterfactual Estimation
• Latent Causal Modeling for 3D Brain MRI Counterfactuals