Research map / Graph learning / Graph self-supervised learning
GOCM: Single-Step Graph Outlier Synthesis via Origin Consistency Model
Yifan Li, Zhihui Wang, Changmiao Wang, Guangxiao Ma, Peng 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 Origin Consistency in place of the standard Consistency Model (ablation) | GATSep + GOCM · Weibo | AUC: 99.52 -> 99.62 | Improved |
| add Origin Consistency in place of the standard Consistency Model (ablation) | GATSep + GOCM · Weibo | AP: 97.43 -> 97.92 | Improved |
| add Origin Consistency in place of the standard Consistency Model (ablation) | GATSep + GOCM · Tolokers | AUC: 82.73 -> 83.69 | Improved |
| add Origin Consistency in place of the standard Consistency Model (ablation) | GATSep + GOCM · Tolokers | AP: 53.55 -> 55.39 | Improved |
| add CM-based synthetic outliers to the GATSep detector (ablation) | GATSep · Weibo | AUC: 96.72 -> 99.52 | Improved |
| swap GODM for GOCM augmentation | GOCM vs GODM · Tolokers | AP: 52.95 -> 55.39 | Improved |
| swap GODM for GOCM augmentation | GOCM vs GODM · Elliptic | AUC: 89.77 -> 88.40 | Hurt |
| swap GODM for GOCM augmentation | GOCM vs GODM · Questions | AP: 20.48 -> 19.39 | Hurt |
| swap GODM for GOCM augmentation | GOCM vs GODM · Yelp | AP: 64.64 -> 72.15 | Improved |
| augment GCN with GOCM instead of GODM | GCN · Tolokers | AP: 44.17 -> 49.40 | Improved |
| augment GAT with GOCM instead of GODM | GAT · Tolokers | AP: 51.13 -> 52.54 | Improved |
| augment DCI with GODM | DCI · Tolokers | AUC: 73.75 (-2.23) | Hurt |
Closest papers by meaning
- ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection (AAAI 2024 · similarity 0.87)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.87)
- Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy (NeurIPS 2024 · similarity 0.87)
- Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark (ICLR 2025 · similarity 0.86)
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.86)
- ROG_PL: Robust Open-Set Graph Learning via Region-Based Prototype Learning (AAAI 2024 · similarity 0.86)
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.
