AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Towards Multiple Missing Values-resistant Unsupervised Graph Anomaly Detection

Jiazhen Chen, Xiuqin Liang, Sichao Fu, Zheng Ma, Weihua Ou

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection · 1 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 structure reconstruction pathway (PPR diffusion) (ablation)M2V-UGAD · Cora, Citeseer, Books, Disney (30% missing)AUROC: about 10-30% AUROC lower without itImproved
add feature imputation pathway (ablation)M2V-UGAD · Cora, Citeseer, Books, Disney (30% missing)AUROC: about 3-10% AUROC lower without itImproved
add pseudo-anomaly generation (ablation)M2V-UGAD · Cora, Citeseer, Books, Disney (30% missing)AUROC: about 10-35% AUROC lower without itImproved
add feature imputation loss Lfeat (ablation)M2V-UGAD · Cora, Citeseer, Books, Disney (30% missing)AUROC: about 2-4% AUROC lower without itImproved
add reconstruction loss Lrecon (ablation)M2V-UGAD · Cora, Citeseer, Books, Disney (30% missing)AUROC: about 2-4% AUROC lower without itImproved
M2V-UGAD vs ADA-GAD with ASD-VAE imputationM2V-UGAD · Books (30% missing)AUROC: 0.70 -> 0.63Hurt
M2V-UGAD vs best impute-then-detect baselineM2V-UGAD · Cora (30% missing)AUROC: 0.84 -> 0.93Improved
M2V-UGAD vs best impute-then-detect baselineM2V-UGAD · Flickr (30% missing)AUROC: 0.74 -> 0.93Improved
raise missing rate from 10% to 50%M2V-UGAD · CoraAUROC: 0.93 -> 0.92No clear effect
raise missing rate from 10% to 50% for ADA-GADADA-GAD · CoraAUROC: 0.86 -> 0.83Hurt
increase imputation loss weight alpha above 0.01 (ablation)M2V-UGAD · Cora, Citeseer, Books, DisneyAUROCHurt
increase pseudo-anomaly ratio eta from 0.1 to 0.5 (ablation)M2V-UGAD · DisneyAUROCHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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