AI Paper Atlas

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

AAAI 2026 · Graph learning › GNN architectures · approach: Graph structure learning · 0 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
plug HSADP adapter into HeCoHeCo · ACM (10-shot)Macro-F1: 87.76 -> 90.39Improved
plug HSADP adapter into HeCoHeCo · DBLP (10-shot)Macro-F1: 89.56 -> 88.41Hurt
plug HSADP adapter into HEROHERO · DBLP (10-shot)Macro-F1: 86.28 -> 89.18Improved
plug HSADP adapter into HGMAEHGMAE · Freebase (10-shot)Macro-F1: 47.33 -> 52.64Improved
plug HSADP adapter into HGCMLHGCML · ACM (20-shot)Macro-F1: 90.43 -> 91.28Improved
plug HSADP adapter into HANHAN · ACMAUC: 90.25 -> 96.98Improved
plug HSADP adapter into HGTHGT · YelpMicro-F1: 86.63 -> 84.01Hurt
remove homogeneous subgraph enhancer (HoSE) (ablation)HSADP · ACM and DBLPMacro-F1, Micro-F1, AUCImproved
remove heterogeneous edge discriminator (HeED) (ablation)HSADP · ACM and DBLPMacro-F1, Micro-F1, AUCImproved
vary similarity threshold eta (ablation)HSADP · ACM and DBLPMacro-F1Mixed

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