Research map / Probabilistic and scientific modeling / Treatment effects
IGC-Net for conditional average potential outcome estimation over time
Konstantin Hess, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
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 IGC-Net instead of best baseline under high confounding | IGC-Net · Tumor growth synthetic (gamma=20) | RMSE: 4.24 -> 3.71 | Improved |
| use IGC-Net on high-dimensional MIMIC-III semi-synthetic data | IGC-Net · MIMIC-III semi-synthetic (N=3000, tau=6) | RMSE: 0.60 -> 0.48 | Improved |
| iterative G-computation instead of inverse propensity weighting (RMSNs) | IGC-Net · MIMIC-III semi-synthetic (N=1000, tau=6) | RMSE: 1.02 -> 0.54 | Improved |
| regression-based G-computation instead of distribution estimation (G-Net) | IGC-Net · MIMIC-III semi-synthetic (N=1000, tau=6) | RMSE: 1.03 -> 0.54 | Improved |
| use IGC-Net on real-world factual prediction | IGC-Net · MIMIC-III real-world factual | RMSE: 9.14 vs CT 9.05 (N=3000, tau=2) | No clear effect |
| add iterative generation and learning steps (vs biased transformer without adjustment) (ablation) | IGC-Net · semi-synthetic | RMSE | Improved |
| replace multi-input transformer with LSTM backbone (ablation) | IGC-Net · semi-synthetic | RMSE | No clear effect |
| IGC-Net under severe overlap violation (rho 0.6) | IGC-Net · Tumor growth overlap sensitivity | RMSE: 2.78 vs CT 2.72 | Mixed |
Closest papers by meaning
- Stabilized Neural Prediction of Potential Outcomes in Continuous Time (ICLR 2025 · similarity 0.88)
- PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect (ICML 2024 · similarity 0.84)
- Adjustment for Confounding using Pre-Trained Representations (ICML 2025 · similarity 0.83)
- Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data (NeurIPS 2025 · similarity 0.83)
- Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation (AAAI 2024 · similarity 0.83)
- GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting (NeurIPS 2026 · similarity 0.82)
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.
