AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Self-Supervised Hypergraph Learning with Substructure Awareness for Hyperedge Prediction

Ming Li, Huiting Wang, Yuting Chen, Lu Bai, Lixin Cui, Feilong Cao, Ke Lv

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 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
add SCHA and A3CL to baseline (ablation)S3Hyper · Coraaverage AUROC: 0.697 -> 0.829Improved
add SCHA (substructure-contextualized aggregator) (ablation)S3Hyper w/o SCHA · Coraaverage AUROC: 0.724 -> 0.829Improved
add A3CL (tri-directional contrastive learning) (ablation)S3Hyper w/o A3CL · Citeseeraverage AUROC: 0.833 -> 0.861Improved
add A3CL (ablation)S3Hyper w/o A3CL · NDC-classaverage AUROC: 0.857 -> 0.862Improved
add SCHA (ablation)S3Hyper w/o SCHA · NDC-classaverage AUROC: 0.778 -> 0.862Improved
add A3CL (ablation)S3Hyper w/o A3CL · DBLP SNSAUROC: 0.849 -> 0.880No clear effect
replace mean/max-min/attention aggregation with SCHA (ablation)S3Hyper · CiteseerAUROC: 0.85 -> 0.86 (attention vs SCHA)Improved
replace best other aggregator with SCHA (ablation)S3Hyper · NDC-class / DBLPAUROC: SCHA 0.86 / 0.82Improved
vary contrastive loss weights lambda in [0.1, 1.0] (ablation)S3Hyper · NDC-class, CoraAUROCNo clear effect
S3Hyper vs CASH on CiteseerS3Hyper · Citeseer SNSAUROC: CASH 0.925 vs S3Hyper 0.940 (NHP 0.991 best)Hurt
use S3Hyper instead of CASHS3Hyper · NDC-classaverage AUROC: 0.752 -> 0.862Improved

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