Research map / Graph learning / Graph self-supervised learning
DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
Xuanwen Huang, Yang Yang, Yang Wang, Chunping Wang, Zhisheng Zhang, Jiarong Xu, Lei Chen, Michalis Vazirgiannis
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 |
|---|---|---|---|
| use graph structure with node features (GCN) instead of MLP | MLPs · DGraph test | AUC: 0.723 -> 0.751 | Improved |
| use dynamic (temporal) information via TGAT instead of GCN | GCN · DGraph test | AUC: 0.751 -> 0.792 | Improved |
| use specialized GAD methods instead of general GNNs | GCN/SAGE · DGraph test | AUC: 0.778 -> 0.752 | Hurt |
| add background-node indicator feature (ablation) | GCN · DGraph test | AUC: 0.751 -> 0.768 | Improved |
| add background-node indicator feature (ablation) | GCN · DGraph test | AP: 0.037 -> 0.037 | No clear effect |
| treat background nodes as separate node type with RGCN (ablation) | GCN · DGraph test | AUC: 0.751 -> 0.784 | Improved |
| remove increasing proportion of background nodes (ablation) | GCN · DGraph test | AUC: 0.76 -> 0.72 | Hurt |
| add missing-value flags and imputation tricks (ablation) | GCN · DGraph test | AUC: +0.39% AUC | Improved |
| add missing-value flags and imputation tricks (ablation) | MLP · DGraph test | AUC: +0.11% AUC | Improved |
Closest papers by meaning
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.92)
- UniGAD: Unifying Multi-level Graph Anomaly Detection (NeurIPS 2024 · similarity 0.88)
- Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection (ICML 2025 · similarity 0.88)
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.88)
- Open-Set Graph Anomaly Detection via Normal Structure Regularisation (ICLR 2025 · similarity 0.87)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (ICLR 2025 · 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.
