Reproduce “Generative Semi-supervised Graph Anomaly Detection” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hezhe Qiao, Qingsong Wen, Xiaoli Li, Ee-Peng Lim, Guansong Pang
GGAD detects graph anomalies using labeled normal nodes without requiring anomaly labels. It generates pseudo-anomaly representations from normal nodes’ neighborhoods, then trains a one-class classifier with local-affinity and egocentric-closeness assumptions. Across six real-world datasets, it leads in AUROC on all six and AUPRC on five; OCGNN has higher AUPRC on Photo, and results are benchmark evaluations, not deployment evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.