AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

HyperGOOD: Towards Out-of-Distribution Detection in Hypergraphs

Tingyi Cai, Yunliang Jiang, Ming Li, Changqin Huang, Yujie Fang, Chengling Gao, Zhonglong Zheng

AAAI 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 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
HyperGOOD vs best baseline under feature perturbationHyperGOOD · House (feature perturbation)AUC: 0.8506 -> 0.9832Improved
HyperGOOD vs graph OOD baselines on PubmedHyperGOOD · Pubmed (feature perturbation)AUC: 0.5397 -> 0.5323Hurt
HyperGOOD vs best baseline under label perturbationHyperGOOD · Cora-CA (label perturbation)AUC: 0.5402 -> 0.5313Hurt
HyperGOOD vs best baseline under label perturbationHyperGOOD · Senate (label perturbation)AUC: 0.5373 -> 0.9563Improved
add structure-aware energy propagation (ablation)HyperGOOD · House and Senate energy score distributionsIND/OOD separabilityImproved
apply graph OOD detectors to clique-expanded hypergraphsGNNSafe and NODESAFE · House (feature perturbation)IND/OOD score separation: 0.8506 -> 0.9832Hurt
vary lambda and alpha (ablation)HyperGOOD · Cora (feature perturbation)AUCNo clear effect
MSP and ODIN under label perturbationMSP · label perturbation, most datasetsAUC: 0.5000No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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