Research map / Graph learning / Graph self-supervised learning
Uncovering Specific-Shape Graph Anomalies in Attributed Graphs
Nannan Wu, Wenjun Wang, Feng Chen, Jianxin Li, Bo Li, Jinpeng Huai
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 |
|---|---|---|---|
| Query-map instead of Top-K | graph anomaly detection · Emergency Q2 10% noise | running time (s): 6,640.92 -> 0.74 | Improved |
| Query-map (EBP) instead of Fast-K | graph anomaly detection · Water Pollution 10% noise Q3 | running time (s): 190.54 -> 21.92 | Improved |
| Fast-K instead of Query-map (EBP) on simplest query | graph anomaly detection · Water Pollution 2% noise Q1 | running time (s): 7.99 -> 2.37 | Improved |
| Query-map (KULL) instead of Query-map (EBP) | Query-map · Emergency 10% noise Q1 | running time (s): 0.73 -> 0.35 | Improved |
| raise noise level from 2% to 10% | Query-map (EBP) · Water Pollution Q1 | running time (s): 7.99 -> 8.18 | No clear effect |
| raise noise level from 2% to 10% | Top-K · Water Pollution Q3 vs Q1 | running time (s): 33.27 -> 56.62 | Hurt |
| Query-map instead of best baseline at Water Pollution Q3 (precision, 2% noise) | graph anomaly detection · Water Pollution 2% noise Q3 | precision | No clear effect |
| Query-map (EBP) instead of best baseline on Emergency data, 10% noise | graph anomaly detection · Emergency 10% noise | precision: at least 0.27 improvement | Improved |
| Query-map (KULL) instead of best baseline on Emergency data, 10% noise | graph anomaly detection · Emergency 10% noise | precision | No clear effect |
| grow query graph size Q1 to Q3 on Water Pollution, 10% noise | Query-map · Water Pollution 10% noise | precision: increase to 1.0 | Improved |
| grow query graph size on Water Pollution 2% noise | Fast-K and Top-K · Water Pollution 2% noise | precision | Hurt |
Closest papers by meaning
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.87)
- UniGAD: Unifying Multi-level Graph Anomaly Detection (NeurIPS 2024 · similarity 0.87)
- Graph Anomaly Detection via Prototype-Aware Label Propagation (Student Abstract) (AAAI 2024 · similarity 0.86)
- CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection (ICML 2025 · similarity 0.86)
- Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection (ICML 2025 · similarity 0.86)
- Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy (NeurIPS 2024 · similarity 0.85)
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.
