Research map / Graph learning / Graph self-supervised learning
Binary Message Passing for Generalizable Semi-Supervised Graph Anomaly Detection
Jingyuan Zhang, Xin Wang, Lei Yu, Li Yang, Fengjun 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 multi-scale BMP trees (forest) to the single tree (ablation) | BMP · T-Social | AP: 32.55 -> 87.13 | Improved |
| add multi-scale BMP trees (ablation) | BMP · YelpChi | AP: 42.55 -> 44.46 | Improved |
| add multi-scale BMP trees (ablation) | BMP · Amazon | AP: 83.18 -> 85.26 | Improved |
| add consistency loss (ablation) | BMP · Amazon | AP: 72.79 -> 85.26 | Improved |
| add consistency loss (ablation) | BMP · T-Social | AP: 82.40 -> 87.13 | Improved |
| add consistency loss (ablation) | BMP · YelpChi | AP: 42.32 -> 44.46 | Improved |
| add consistency loss (ablation) | BMP · T-Finance | AP: 84.78 -> 86.51 | Improved |
| binary message routing replaces broadcast routing (BMP vs SpaceGNN) | BMP · YelpChi | AP: 36.01 -> 44.46 | Improved |
| increase BMP depth p from 1 to 3 (ablation) | BMP · T-Social | AP | Improved |
| increase BMP depth p from 1 to 3 (ablation) | BMP · smaller graphs (YelpChi, Amazon, T-Finance) | AP | No clear effect |
| vary index update interval T from 10 to 90 (ablation) | BMP · all datasets | AP | No clear effect |
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 8 of 8 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
- Partitioning Message Passing for Graph Fraud Detection (ICLR 2024 · similarity 0.89)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.89)
- Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection (ICML 2025 · similarity 0.88)
- ARC: A Generalist Graph Anomaly Detector with In-Context Learning (NeurIPS 2024 · similarity 0.88)
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.88)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (ICLR 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.
