Research map / Probabilistic and scientific modeling / Causal discovery
Learning Representations for Counterfactual Inference
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add imbalance penalty to representation (BNN-2-2 vs NN-4) (ablation) | neural network · IHDP | PEHE: 1.9 -> 1.6 | Helped |
| add imbalance penalty to representation (BNN-2-2 vs NN-4) (ablation) | neural network · IHDP | ITE RMSE: 2.0 -> 1.7 | Helped |
| add imbalance penalty (BNN-2-2 vs NN-4) (ablation) | neural network · News | PEHE: 3.8 -> 2.0 | Helped |
| add imbalance penalty (BNN-2-2 vs NN-4) (ablation) | neural network · News | ITE RMSE: 2.8 -> 2.0 | Helped |
| add imbalance penalty (BNN-2-2 vs NN-4) (ablation) | neural network · IHDP | ATE absolute error: 0.5 -> 0.3 | Helped |
| add imbalance penalty (BNN-2-2 vs NN-4) (ablation) | neural network · News | ATE absolute error: 1.1 -> 0.3 | Helped |
| balanced variable selection (BLR) vs Lasso + Ridge | linear model · IHDP | ITE RMSE: 2.8 -> 2.8 | No clear effect |
| balanced variable selection (BLR) vs Lasso + Ridge | linear model · News | ITE RMSE: 2.2 -> 2.2 | No clear effect |
| balance-regularized linear-hidden network BNN-4-0 vs standard NN-4 | neural network · News | ITE RMSE: 2.8 -> 2.1 | Helped |
| balance-regularized linear BNN-4-0 vs OLS | linear outcome · IHDP | ITE RMSE: 4.6 -> 3.0 | Helped |
| non-linear (BNN-2-2) vs linear (BNN-4-0) outcome model | BNN · IHDP | PEHE: 5.6 -> 1.6 | Helped |
| BNN-2-2 vs BART | BART · News | ITE RMSE: 5.8 -> 2.0 | Helped |
Closest papers by meaning
- Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models (ICLR 2024 · similarity 0.86)
- LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching (NeurIPS 2025 · similarity 0.86)
- Learning Counterfactual Outcomes Under Rank Preservation (NeurIPS 2025 · similarity 0.85)
- From Black-box to Causal-box: Towards Building More Interpretable Models (NeurIPS 2025 · similarity 0.85)
- Causal Contrastive Learning for Counterfactual Regression Over Time (NeurIPS 2024 · similarity 0.85)
- Counterfactual Generative Modeling with Variational Causal Inference (ICLR 2025 · similarity 0.85)
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.