Research map / Probabilistic and scientific modeling / Causal discovery
Deep Structural Causal Models for Tractable Counterfactual Inference
Nick Pawlowski, Daniel Coelho de Castro, Ben Glocker
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Condition image generation on thickness and intensity (ablation) | Independent Morpho-MNIST model · Morpho-MNIST | log p(x|t,i) lower bound: -5919.14 -> -5520.37 | Improved |
| Add a causal dependency from thickness to intensity (ablation) | Conditional Morpho-MNIST model · Morpho-MNIST | log p(i|t): -5.19 -> -4.30 | Improved |
| Use the full causal model instead of an independent model (ablation) | Morpho-MNIST · Morpho-MNIST counterfactual, do(t+2) | counterfactual image MAE: 41.6 -> 17.6 | Improved |
| Add the thickness-to-intensity dependency to the conditional model (ablation) | Conditional Morpho-MNIST model · Morpho-MNIST counterfactual, do(t+2) | counterfactual image MAE: 31.8 -> 17.6 | Improved |
Closest papers by meaning
- Counterfactual Generative Modeling with Variational Causal Inference (ICLR 2025 · similarity 0.88)
- Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models (ICLR 2024 · similarity 0.88)
- Cyclic Counterfactuals under Shift–Scale Interventions (NeurIPS 2025 · similarity 0.87)
- Learning Structural Causal Models from Ordering: Identifiable Flow Models (AAAI 2025 · similarity 0.87)
- From Black-box to Causal-box: Towards Building More Interpretable Models (NeurIPS 2025 · similarity 0.86)
- Causal Representation Learning via Counterfactual Intervention (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
