Research map / Probabilistic and scientific modeling / Treatment effects
Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment
Yuan Chen, Donglin Zeng, Tianchen Xu, Yuanjia Wang
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 latent-representation ITR instead of CausalForest | ITR learner · Simulation N=200 | latent severity value (lower better): 1.85 -> 1.80 | Improved |
| Use latent-representation ITR instead of CausalForest | ITR learner · Simulation N=2000 | latent severity value (lower better): 1.79 -> 1.74 | Improved |
| Use proposed method instead of Deep-A | ITR learner · Simulation N=200 | predictive symptoms value: 13.62 -> 12.74 | Improved |
| Increase training size from 200 to 2000 | Proposed · Simulation | latent severity value: 1.80 -> 1.74 | Improved |
| Increase training size from 500 to 2000 | baselines (Deep-O) · Simulation | latent severity value: 1.80 -> 1.79 | No clear effect |
| Increase training size from 200 to 2000 | Proposed · Simulation | predictive symptoms value: 12.74 -> 12.52 | Improved |
| Use proposed method instead of CausalForest | ITR learner · STAR*D | HAMD: 12.62 -> 12.23 | Improved |
| Use proposed method instead of TARNet | ITR learner · STAR*D | QIDS: 8.63 -> 8.33 | Improved |
| Use proposed method instead of CausalForest | ITR learner · STAR*D | CGI: 2.72 -> 2.54 | Improved |
| Use proposed method instead of CausalForest | ITR learner · STAR*D | WSAS: 19.98 -> 20.27 | Hurt |
| Use proposed method instead of Deep-A | ITR learner · STAR*D | HAMD: 12.32 -> 12.23 | No clear effect |
| Use proposed method instead of Deep-O | ITR learner · STAR*D | HAMD: 13.59 -> 12.23 | Improved |
Closest papers by meaning
- On Inductive Biases for Heterogeneous Treatment Effect Estimation (NeurIPS 2021 · similarity 0.87)
- PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect (ICML 2024 · similarity 0.85)
- Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing (AAAI 2024 · similarity 0.84)
- Adversarially Balanced Representation for Continuous Treatment Effect Estimation (AAAI 2024 · similarity 0.84)
- MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis (NeurIPS 2025 · similarity 0.84)
- Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner (NeurIPS 2024 · similarity 0.83)
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.
