AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Normality Calibration in Semi-supervised Graph Anomaly Detection

Guolei Zeng, Hezhe Qiao, Guoguo Ai, Jinsong Guo, Guansong Pang

ICML 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 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 ScoreDA and NormReg (full GraphNC) on top of the GGAD teacherGGAD · Average over 6 datasetsAUROC: 0.7003 -> 0.7533Improved
add ScoreDA and NormReg (full GraphNC) on top of the GGAD teacherGGAD · Average over 6 datasetsAUPRC: 0.2745 -> 0.3610Improved
add ScoreDA to the teacher (ablation)GGAD · TolokersAUROC: 0.5340 -> 0.5811Improved
add NormReg to ScoreDA (student) after ScoreDA only (ablation)OT+ScoreDA · TolokersAUROC: 0.5811 -> 0.6505Improved
add NormReg to ScoreDA on Amazon (ablation)OT+ScoreDA · AmazonAUROC: 0.9511 -> 0.9613Improved
add NormReg to ScoreDA on T-Finance (ablation)OT+ScoreDA · T-FinanceAUPRC: 0.2566 -> 0.3667Improved
apply NormReg to labeled normal nodes only instead of all nodes (ablation)GraphNC · T-FinanceAUPRC: 0.1971 -> 0.3667Improved
add NormReg directly to teacher pre-training without ScoreDA (ablation)GGAD · AmazonAUROC: 0.9443 -> 0.8956Hurt
add NormReg directly to teacher pre-training without ScoreDA (ablation)GGAD · T-FinanceAUROC: 0.8228 -> 0.8455Improved
plug GraphNC into DOMINANT teacherDOMINANT · Average over 6 datasetsAUROC: 0.6162 -> 0.7088Improved
plug GraphNC into OCGNN teacherOCGNN · Average over 6 datasetsAUROC: 0.6265 -> 0.6956Improved
apply GraphNC to degraded GGAD teacher with anomalies injected into labeled normalsGGAD* · Average over 6 datasetsAUROC: 0.5008 -> 0.6411Improved

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