Research map / Label-efficient and robust learning / Domain adaptation and generalization
Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Ioana Bica, Mihaela van der Schaar
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 |
|---|---|---|---|
| add PO sharing layers across domains (ablation) | HTCE-T-Learner · Twins | PEHE: 0.15 -> 0.06 | Improved |
| add PO sharing layers across domains (ablation) | HTCE-DR-Learner · Twins | PEHE: 0.11 -> 0.05 | Improved |
| add PO sharing layers across domains (ablation) | HTCE-S-Learner · Twins | PEHE: 0.18 -> 0.12 | Improved |
| add PO sharing layers across domains (ablation) | HTCE-TARNet · Twins | PEHE: 0.12 -> 0.09 | Improved |
| add orthogonal regularization on shared/private representations (ablation) | HTCE-T-Learner · Twins | PEHE: 0.08 -> 0.06 | Improved |
| add orthogonal regularization on shared/private representations (ablation) | HTCE-TARNet · Twins | PEHE: 0.11 -> 0.09 | Improved |
| add orthogonal regularization on PO layers (ablation) | HTCE-T-Learner · Twins | PEHE: 0.11 -> 0.06 | Improved |
| add orthogonal regularization on PO layers (ablation) | HTCE-DR-Learner · Twins | PEHE: 0.10 -> 0.05 | Improved |
| use heterogeneous transfer (HTCE) instead of target-only training | DR-Learner · Twins | PEHE: 0.20 -> 0.05 | Improved |
| use only shared features instead of target features | DR-Learner · Twins | PEHE: 0.20 -> 0.46 | Hurt |
| replace RadialGAN translation with HTCE | T-Learner · Twins | PEHE: 0.2 -> 0.06 | Improved |
| RadialGAN translation versus target-only training | TARNet · Twins | PEHE: 0.19 -> 0.19 | No clear effect |
Closest papers by meaning
- Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environments (ICML 2024 · similarity 0.87)
- Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data (NeurIPS 2025 · similarity 0.87)
- Model-agnostic meta-learners for estimating heterogeneous treatment effects over time (ICLR 2025 · similarity 0.87)
- Learning Representations of Instruments for Partial Identification of Treatment Effects (ICML 2025 · similarity 0.87)
- Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation (ICLR 2024 · similarity 0.87)
- A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding (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.
