Research map / Label-efficient and robust learning / Domain adaptation and generalization
Heterogeneous Transfer Learning with Weighted Instance-Correspondence Data
Yuwei He, Xiaoming Jin, Guiguang Ding, Yuchen Guo, Jungong Han, Jiyong Zhang, Sicheng Zhao
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 meta-learner updates of the feature transformation (ablation) | TLWCsup · Webis-CLS-10 EJM | accuracy (%): 79.04 -> 80.94 | Improved |
| add meta-learner updates of the feature transformation (ablation) | TLWCsup · Webis-CLS-10 EFB | accuracy (%): 84.92 -> 84.50 | Hurt |
| add meta-learner updates of the feature transformation (ablation) | TLWCsup · Webis-CLS-10 EFD | accuracy (%): 84.41 -> 85.00 | Improved |
| add meta-learner updates of the feature transformation (ablation) | TLWCsup · MRC FR | accuracy (%): 76.47 -> 78.70 | Improved |
| add meta-learner updates of the feature transformation (ablation) | TLWCsup · MRC IT | accuracy (%): 61.77 -> 68.83 | Improved |
| add meta-learner updates of the feature transformation (ablation) | TLWCsup · MRC GE | accuracy (%): 71.10 -> 70.08 | Hurt |
| add meta-learner updates of the feature transformation (ablation) | TLWCsup · MRC SP | accuracy (%): 67.37 -> 69.40 | Improved |
| TLWC instead of HHTL | HHTL · MRC IT | accuracy (%): 61.80 -> 68.83 | Improved |
| TLWC instead of HHTL | HHTL · Webis-CLS-10 EJM | accuracy (%): 79.32 -> 80.94 | Improved |
| TLWC instead of HHTL | HHTL · MRC GE | accuracy (%): 69.47 -> 70.08 | Improved |
| deep-model features (HHTL) instead of DATN | DATN · Webis-CLS-10 EFB | accuracy (%): 78.47 -> 83.63 | Improved |
| learned IC weights under artificial mismatch noise (n_e up to 32) | TLWCsup · text->DeCAF6 NUS-WIDE | accuracy (%) | Improved |
Closest papers by meaning
- Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning (NeurIPS 2018 · similarity 0.85)
- Transfer Learning via Minimizing the Performance Gap Between Domains (NeurIPS 2019 · similarity 0.85)
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.83)
- Transfer Learning Through Conditional Quantile Matching (NeurIPS 2026 · similarity 0.82)
- A Unified Framework for Heterogeneous Semi-supervised Learning (CVPR 2025 · similarity 0.82)
- Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation (NeurIPS 2025 · 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.
