Research map / Graph learning / Graph self-supervised learning
Semi-supervised Credit Card Fraud Detection via Attribute-Driven Graph Representation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GTAN instead of PC-GNN | Fraud detection models · YelpChi | AUC: 0.8174 -> 0.9241* | Helped |
| Use GTAN instead of PC-GNN | Fraud detection models · Amazon | AUC: 0.9581 -> 0.9630* | Helped |
| Use GTAN instead of PC-GNN | Fraud detection models · FFSD | AUC: 0.6795 -> 0.7616* | Helped |
| Use GTAN instead of PC-GNN | Fraud detection models · YelpChi | AP: 0.4810 -> 0.7513* | Helped |
| Use GTAN instead of PC-GNN | Fraud detection models · Amazon | AP: 0.8549 -> 0.8838* | Helped |
| Use GTAN instead of PC-GNN | Fraud detection models · FFSD | AP: 0.4487 -> 0.5767* | Helped |
| Add temporal graph attention to adaptively weight neighboring transactions (ablation) | GTAN · YelpChi, Amazon, and FFSD | fraud detection performance | Helped |
| Add risk embeddings to propagate labeled transaction risk (ablation) | GTAN · YelpChi, Amazon, and FFSD | fraud detection performance | Helped |
| Use two temporal graph attention layers rather than deeper stacks (ablation) | GTAN · FFSD | AUC and AP | Mixed |
| Increase temporal edges per node up to six (ablation) | GTAN · FFSD | fraud detection performance | Helped |
| Increase temporal edges per node beyond six (ablation) | GTAN · FFSD | fraud detection performance | Hurt |
| Vary training-label ratio from 10% to 80% (ablation) | GTAN · YelpChi and Amazon | AUC | Helped |
Closest papers by meaning
- Barely Supervised Learning for Graph-Based Fraud Detection (AAAI 2024 · similarity 0.88)
- Dynamic Neighborhood Modeling via Node-Subgraph Contrastive Learning for Graph-Based Fraud Detection (AAAI 2025 · similarity 0.87)
- Context-aware Graph Neural Network for Graph-based Fraud Detection with Extremely Limited Labels (AAAI 2025 · similarity 0.87)
- Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum (AAAI 2024 · similarity 0.87)
- DiG-In-GNN: Discriminative Feature Guided GNN-Based Fraud Detector against Inconsistencies in Multi-Relation Fraud Graph (AAAI 2024 · similarity 0.87)
- DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection (AAAI 2024 · similarity 0.85)
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.