AI Paper Atlas

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

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
add PO sharing layers across domains (ablation)HTCE-T-Learner · TwinsPEHE: 0.15 -> 0.06Improved
add PO sharing layers across domains (ablation)HTCE-DR-Learner · TwinsPEHE: 0.11 -> 0.05Improved
add PO sharing layers across domains (ablation)HTCE-S-Learner · TwinsPEHE: 0.18 -> 0.12Improved
add PO sharing layers across domains (ablation)HTCE-TARNet · TwinsPEHE: 0.12 -> 0.09Improved
add orthogonal regularization on shared/private representations (ablation)HTCE-T-Learner · TwinsPEHE: 0.08 -> 0.06Improved
add orthogonal regularization on shared/private representations (ablation)HTCE-TARNet · TwinsPEHE: 0.11 -> 0.09Improved
add orthogonal regularization on PO layers (ablation)HTCE-T-Learner · TwinsPEHE: 0.11 -> 0.06Improved
add orthogonal regularization on PO layers (ablation)HTCE-DR-Learner · TwinsPEHE: 0.10 -> 0.05Improved
use heterogeneous transfer (HTCE) instead of target-only trainingDR-Learner · TwinsPEHE: 0.20 -> 0.05Improved
use only shared features instead of target featuresDR-Learner · TwinsPEHE: 0.20 -> 0.46Hurt
replace RadialGAN translation with HTCET-Learner · TwinsPEHE: 0.2 -> 0.06Improved
RadialGAN translation versus target-only trainingTARNet · TwinsPEHE: 0.19 -> 0.19No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy