Research map / Graph learning / Graph self-supervised learning
HSMAD: Heterophily-Driven Spectral and Manifold Learning for Graph Anomaly Detection
Chen Zhu, Yaying Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Heterophily-Weighted Spectral Filtering (HWSF) (ablation) | HSMAD · Average of 6 datasets | F1-Macro: 0.8809 -> 0.8953 | Improved |
| add Heterophily-Routed Manifold Update (HRMU) (ablation) | HSMAD · Average of 6 datasets | F1-Macro: 0.8801 -> 0.8953 | Improved |
| add HWSF (ablation) | HSMAD · Average of 6 datasets | AUROC: 0.9482 -> 0.9549 | Improved |
| add HRMU (ablation) | HSMAD · Average of 6 datasets | AUROC: 0.9456 -> 0.9549 | Improved |
| add HWSF (ablation) | HSMAD · Yelp | F1-Macro: 0.8306 -> 0.8682 | Improved |
| add HRMU (ablation) | HSMAD · T-Social | F1-Macro: 0.9249 -> 0.9634 | Improved |
| add HRMU (ablation) | HSMAD · Weibo | AUROC: 0.9900 -> 0.9944 | Improved |
| heterophily-weighted edges versus unweighted or random-weighted edges | HSMAD · Amazon and Yelp subgraphs (2,000 nodes) | spectral energy concentration | Improved |
| increase spectral filter order C | HSMAD · Yelp | F1-Macro and AUROC | Improved |
| vary edge mask quantile tau from 10% to 30% | HSMAD · Yelp | F1-Macro and AUROC | Mixed |
| HSMAD versus PMP and CGADM on very sparse graph | HSMAD · T-Social | AUROC: 0.9888 vs 0.9946 (PMP) | Hurt |
Closest papers by meaning
- Semi-supervised Graph Anomaly Detection via Robust Homophily Learning (NeurIPS 2025 · similarity 0.90)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (ICLR 2025 · similarity 0.89)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.89)
- CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection (ICML 2025 · similarity 0.88)
- ARC: A Generalist Graph Anomaly Detector with In-Context Learning (NeurIPS 2024 · similarity 0.88)
- Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection (ICML 2025 · similarity 0.88)
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.
