Research map / Graph learning / Knowledge and temporal graphs
Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks
Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Russ Salakhutdinov, Bryan Perozzi
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 KTN domain adaptation to HMPNN | HMPNN · OAG-CS P-A (L1) | MRR: 0.297 -> 0.629 | Improved |
| add KTN to HMPNN | HMPNN · OAG-CS V-A (L1) | MRR: 0.133 -> 0.586 | Improved |
| add KTN to HMPNN | HMPNN · PubMed G-D | MRR: 0.354 -> 0.445 | Improved |
| add KTN to HAN | HAN · OAG-CS P-A (L1) | MRR: 0.047 -> 0.497 | Improved |
| add KTN to MAGNN | MAGNN · OAG-CS P-A (L1) | MRR: 0.378 -> 0.556 | Improved |
| add KTN to R-GCN | R-GCN · OAG-CS P-A (L1) | NDCG: 0.337 -> 0.577 | Improved |
| add KTN to MPNN | MPNN · OAG-CS A-P (L1) | MRR: 0.145 -> 0.595 | Improved |
| replace KTN with DAN (MMD-based DA) | HMPNN · OAG-CS P-A (L1) | NDCG: 0.623 -> 0.452 | Hurt |
| replace MMD-based DA with adversarial DANN | HMPNN · OAG-CS P-A (L1) | NDCG: 0.452 -> 0.292 | Hurt |
| use label propagation (LP) instead of DA | HMPNN · OAG-CS P-A (L1) | MRR: 0.297 -> 0.041 | Hurt |
| shorten meta-path to length 1 (below minimum 2) (ablation) | KTN · OAG-CS A-V (L1) | MRR: 0.696 -> 0.010 | Hurt |
| lengthen meta-path from 2 to 3 (ablation) | KTN · OAG-CS A-V (L1) | MRR: 0.696 -> 0.648 | Hurt |
Closest papers by meaning
- Harnessing Language Model for Cross-Heterogeneity Graph Knowledge Transfer (AAAI 2025 · similarity 0.89)
- HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport (ICML 2025 · similarity 0.88)
- Contextual Structure Knowledge Transfer for Graph Neural Networks (AAAI 2025 · similarity 0.88)
- Heterogeneous Graph Neural Network on Semantic Tree (AAAI 2025 · similarity 0.88)
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily (NeurIPS 2026 · similarity 0.87)
- Contrastive Auxiliary Learning with Structure Transformation for Heterogeneous Graphs (AAAI 2025 · similarity 0.87)
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.
