Research map / Graph learning / GNN architectures
Structure-Enhanced Adapter for Self-Supervised Heterogeneous Graph Learning
Fengyu Yan, Di Jin, Xiaobao Wang, Qianhua Tang, Dongxiao He
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 |
|---|---|---|---|
| plug HSADP adapter into HeCo | HeCo · ACM (10-shot) | Macro-F1: 87.76 -> 90.39 | Improved |
| plug HSADP adapter into HeCo | HeCo · DBLP (10-shot) | Macro-F1: 89.56 -> 88.41 | Hurt |
| plug HSADP adapter into HERO | HERO · DBLP (10-shot) | Macro-F1: 86.28 -> 89.18 | Improved |
| plug HSADP adapter into HGMAE | HGMAE · Freebase (10-shot) | Macro-F1: 47.33 -> 52.64 | Improved |
| plug HSADP adapter into HGCML | HGCML · ACM (20-shot) | Macro-F1: 90.43 -> 91.28 | Improved |
| plug HSADP adapter into HAN | HAN · ACM | AUC: 90.25 -> 96.98 | Improved |
| plug HSADP adapter into HGT | HGT · Yelp | Micro-F1: 86.63 -> 84.01 | Hurt |
| remove homogeneous subgraph enhancer (HoSE) (ablation) | HSADP · ACM and DBLP | Macro-F1, Micro-F1, AUC | Improved |
| remove heterogeneous edge discriminator (HeED) (ablation) | HSADP · ACM and DBLP | Macro-F1, Micro-F1, AUC | Improved |
| vary similarity threshold eta (ablation) | HSADP · ACM and DBLP | Macro-F1 | Mixed |
Closest papers by meaning
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily (NeurIPS 2026 · similarity 0.93)
- Contrastive Auxiliary Learning with Structure Transformation for Heterogeneous Graphs (AAAI 2025 · similarity 0.91)
- An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs (AAAI 2024 · similarity 0.90)
- HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport (ICML 2025 · similarity 0.90)
- Heterogeneous Graph Neural Network on Semantic Tree (AAAI 2025 · similarity 0.90)
- Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks (AAAI 2024 · similarity 0.90)
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.
