Research map / Graph learning / Graph self-supervised learning
Exploring Domain Generalization and Subpopulation Shift for Generalizable Graph-Level Anomaly Detection
Xiaoxiang Li, Xihe Xie, Hai Wan, Xibin Zhao
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 FGSI (fine-grained subpopulation inference) to GSAT (ablation) | GSAT · GOOD-Motif-Base | ROC-AUC: 73.62 -> 77.98 | Improved |
| add GIB4AD (graph reverse distillation + information bottleneck) to GSAT (ablation) | GSAT · GOOD-Motif-Base | ROC-AUC: 73.62 -> 82.53 | Improved |
| add GIB4AD to GSAT (ablation) | GSAT · DrugOOD-IC50-Scaffold | ROC-AUC: 57.99 -> 67.43 | Improved |
| combine FGSI with GIB4AD (ablation) | GSAT · GOOD-CMNIST-Color | ROC-AUC: 76.29 -> 80.01 | Improved |
| add FGSI to GSAT (ablation) | GSAT · DrugOOD-IC50-Scaffold | ROC-AUC: 57.99 -> 63.76 | Improved |
| use FGS-GLAD instead of traditional GLAD baselines (MUSE, SIGNET) under distribution shift | GLAD · GOOD-CMNIST-Color | F1-Score: 13.57/11.68 -> 61.49 | Improved |
Closest papers by meaning
- Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark (ICLR 2025 · similarity 0.92)
- ARC: A Generalist Graph Anomaly Detector with In-Context Learning (NeurIPS 2024 · similarity 0.90)
- Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection (ICML 2025 · similarity 0.90)
- UniGAD: Unifying Multi-level Graph Anomaly Detection (NeurIPS 2024 · similarity 0.90)
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.89)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.89)
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.
