Research map / Graph learning / Graph self-supervised learning
Dynamic Multi-sample Mixup with Gradient Exploration for Open-set Graph Anomaly Detection
Caiyang Yu, Wei Ju, Haixin Wang, Yifan Wang, Ziyue Qiao
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 pseudo-labeling (PL) (ablation) | DEMO · Photo | AUC-ROC: 0.8616 -> 0.9023 | Improved |
| add pseudo-labeling (PL) (ablation) | DEMO · CS | AUC-ROC: 0.8364 -> 0.9448 | Improved |
| add pseudo-labeling (PL) (ablation) | DEMO · ogbn-arxiv | AUC-ROC: 0.4868 -> 0.6364 | Improved |
| add energy gradient (EG) reweighting (ablation) | DEMO · Photo | AUC-ROC: 0.8849 -> 0.9023 | Improved |
| add energy gradient (EG) reweighting (ablation) | DEMO · Computers | AUC-ROC: 0.8100 -> 0.8439 | Improved |
| add energy gradient (EG) reweighting (ablation) | DEMO · Yelp | AUC-ROC: 0.6637 -> 0.7097 | Improved |
| add multi-sample mixup (Mix) (ablation) | DEMO · Photo | AUC-ROC: 0.8750 -> 0.9023 | Improved |
| add multi-sample mixup (Mix) (ablation) | DEMO · Computers | AUC-ROC: 0.8197 -> 0.8439 | Improved |
| add multi-sample mixup (Mix) (ablation) | DEMO · ogbn-arxiv | AUC-ROC: 0.5061 -> 0.6364 | Improved |
| add all three components (Mix, EG, PL) (ablation) | DEMO · Computers | AUC-ROC: 0.7576 -> 0.8439 | Improved |
| add all three components (Mix, EG, PL) (ablation) | DEMO · Yelp | AUC-ROC: 0.5942 -> 0.7097 | Improved |
| add all three components (Mix, EG, PL) (ablation) | DEMO · Photo | AUC-ROC: 0.8300 -> 0.9023 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SpaceGNN — SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels (ICLR 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.89)
- Open-Set Graph Anomaly Detection via Normal Structure Regularisation (ICLR 2025 · similarity 0.89)
- ARC: A Generalist Graph Anomaly Detector with In-Context Learning (NeurIPS 2024 · similarity 0.88)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (ICLR 2025 · similarity 0.87)
- UniGAD: Unifying Multi-level Graph Anomaly Detection (NeurIPS 2024 · similarity 0.87)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.87)
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.
