Research map / Probabilistic and scientific modeling / Treatment effects
Causal Effect Inference for Structured Treatments
Jean Kaddour, Yuchen Zhu, Qi Liu, Matt Kusner, Ricardo Silva
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 |
|---|---|---|---|
| use SIN instead of GraphITE | GraphITE · SW out-sample | WPEHE@6: 35.94 -> 23.19 | Improved |
| use SIN instead of GNN | GNN · TCGA out-sample | WPEHE@6: 27.57 -> 8.15 | Improved |
| use SIN instead of Zero baseline | Zero · TCGA in-sample | WPEHE@6: 26.63 -> 10.98 | Improved |
| regress with GNN instead of treating treatments as categorical (CAT) | CAT · TCGA in-sample | WPEHE@6: 155.88 -> 30.67 | Improved |
| regress with GNN instead of categorical (CAT) | CAT · SW in-sample | WPEHE@6: 51.75 -> 37.10 | Improved |
| GraphITE instead of GNN | GNN · SW in-sample | WPEHE@6: 37.10 -> 34.81 | Improved |
| GraphITE instead of GNN | GNN · TCGA in-sample | WPEHE@6: 30.67 -> 30.31 | No clear effect |
| GNN, CAT or GraphITE versus Zero baseline | Zero · TCGA out-sample | WPEHE@6: 17.94 -> 27.57 | Hurt |
| increase selection bias kappa (ablation) | CAT · TCGA/SW | WPEHE@6 | Mixed |
| no selection bias (kappa=0, randomized experiment) (ablation) | SIN · SW/TCGA | WPEHE@6 | No clear effect |
Closest papers by meaning
- Coupling Generative Modeling and an Autoencoder with the Causal Bridge (NeurIPS 2025 · similarity 0.87)
- Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale Benchmark (ICLR 2025 · similarity 0.87)
- Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects (NeurIPS 2026 · similarity 0.87)
- Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation (ICLR 2024 · similarity 0.86)
- Learning Representations of Instruments for Partial Identification of Treatment Effects (ICML 2025 · similarity 0.86)
- Conformal Inference of Individual Treatment Effects Using Conditional Density Estimates (AAAI 2025 · 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.
