Research map / Probabilistic and scientific modeling / Treatment effects
PITE: Multi-Prototype Alignment for Individual Treatment Effect Estimation
Fuyuan Cao, Jiaxuan Zhang, Xiaoli Li
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 |
|---|---|---|---|
| replace distribution-level alignment (CFR-Wass) with multi-prototype alignment | CFR-style ITE estimator · IHDP out-of-sample | sqrt PEHE: 0.83(0.08) -> 0.60(0.04) | Improved |
| replace instance-level alignment (CITE) with prototype alignment | CITE · IHDP out-of-sample | sqrt PEHE: 0.67(0.14) -> 0.60(0.04) | Improved |
| replace instance-level alignment (FCCL) with prototype alignment | FCCL · IHDP within-sample | sqrt PEHE: 0.53(0.04) -> 0.51(0.02) | Improved |
| use PITE instead of FCCL | FCCL · IHDP within-sample | ATE error: 0.09(0.01) -> 0.09(0.01) | No clear effect |
| use PITE under higher covariate dispersion | CFR-MMD · Synthetic gamma 0.4 -> 1.2 | sqrt PEHE: 2.54 -> 5.37 vs PITE 2.22 -> 4.99 | Improved |
| use prototype alignment | SITE · Synthetic gamma=1.2 | sqrt PEHE: 6.19(0.15) -> 4.99(0.10) | Improved |
| prototype alignment improves representation uniformity | PITE vs CFRNet · IHDP | uniformity: 0.4734 -> 0.4566 | Improved |
Closest papers by meaning
- PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect (ICML 2024 · similarity 0.88)
- Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation (ICML 2025 · similarity 0.87)
- Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale Benchmark (ICLR 2025 · similarity 0.87)
- Doubly robust identification of treatment effects from multiple environments (ICLR 2025 · similarity 0.87)
- Conformal Inference of Individual Treatment Effects Using Conditional Density Estimates (AAAI 2025 · similarity 0.86)
- Hierarchical and Density-based Causal Clustering (NeurIPS 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.
