AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach

Yujing Liu, Yixin Liu, Yu Zheng, Alan Wee-Chung Liew, Xiaofeng Cao, Shirui Pan

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly 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
replace PCA feature alignment with relational fingerprint (REFI) (ablation)REFI-GAD · Group 2 datasets (Cora, Flickr, Facebook, etc.)AUROC (%): Flickr 71.71 -> 89.61; Cora 53.28 -> 96.14Improved
add SNR-guided domain-adaptive refinement (ablation)REFI-GAD · Group 2 datasetsAUROC (%): Flickr 88.08 -> 89.61; Facebook 93.30 -> 94.67; average improvement of 0.70%Improved
add degree dimension to REFI (ablation)REFI-GAD · FlickrAUROC (%): 79.78 -> 89.61Improved
add global directional consistency to REFI (ablation)REFI-GAD · FlickrAUROC (%): 82.05 -> 89.61Improved
add global directional consistency to REFI (ablation)REFI-GAD · CoraAUROC (%): 96.62 -> 96.14No clear effect
add all five REFI attributes (any single one removed lowers average) (ablation)REFI-GAD · 7 Group 2 datasets averageAUROC (%): 80.52-82.54 (single removed) -> 83.41Improved
increase context size k up to 50 (ablation)REFI-GAD · Citeseer, Weibo, Blog, CS, PhotoAUROC (%)Improved
pre-train on source graphs (vs training-free)REFI-GAD · 14 datasetsAUROC gain: avg +4.67%, 12 of 14 positiveImproved
pre-train on source graphs (vs training-free)ARC, AnomalyGFM, UNPrompt, IA-GGAD · 14 datasetsAUROC gain: ARC +1.20%, IA-GGAD +1.13%, UNPrompt -0.92%, AnomalyGFM -0.12%Mixed
fully cross-domain source training (citation as target)existing generalist GAD baselines · Cora, Citeseer, ACM, CS, PubmedAUROC gain: AnomalyGFM -10.79%, UNPrompt -6.33%, ARC -0.11%, IA-GGAD -0.21%Hurt
fully cross-domain source training with REFIREFI-GAD · Cora, Citeseer, ACM, CS, PubmedAUROC gain: +4.15% averageImproved
remove neighborhood consistency modules from training-free ARC/UNPrompt (ablation)ARC, UNPrompt (training-free) · 14 datasetsaverage AUROCImproved

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