Research map / Graph learning / Graph self-supervised learning
Towards Consumer Loan Fraud Detection: Graph Neural Networks with Role-Constrained Conditional Random Field
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 GRC instead of GCN | Alipay auto-loan fraud detection · Alipay auto-loan, 1,000 training samples | F1-Score: 65.21% -> 77.01% | Helped |
| Use GRC instead of GCN | Alipay auto-loan fraud detection · Alipay auto-loan, 2,000 training samples | F1-Score: 68.79% -> 81.32% | Helped |
| Use GRC instead of GCN | Alipay auto-loan fraud detection · Alipay auto-loan, 3,000 training samples | F1-Score: 70.97% -> 82.83% | Helped |
| Use GRC instead of GCN | Alipay auto-loan fraud detection · Alipay auto-loan, 12,000 training samples | F1-Score: 79.07% -> 85.56% | Helped |
| Add CRF role constraint (ablation) | GRC · Alipay auto-loan, 12,000 training samples | F1 score: 83.83% -> 85.56% | Helped |
| Add edge-attribute neighbor aggregation (ablation) | GRC · Alipay auto-loan, 12,000 training samples | F1 score: 83.68% -> 85.56% | Helped |
| Add relation attention (ablation) | GRC · Alipay auto-loan, 12,000 training samples | F1 score: 84.34% -> 85.56% | Helped |
| Add time-slot attention (ablation) | GRC · Alipay auto-loan, 12,000 training samples | F1 score: 83.44% -> 85.56% | Helped |
Closest papers by meaning
- Context-aware Graph Neural Network for Graph-based Fraud Detection with Extremely Limited Labels (AAAI 2025 · similarity 0.84)
- DiG-In-GNN: Discriminative Feature Guided GNN-Based Fraud Detector against Inconsistencies in Multi-Relation Fraud Graph (AAAI 2024 · similarity 0.83)
- Dynamic Neighborhood Modeling via Node-Subgraph Contrastive Learning for Graph-Based Fraud Detection (AAAI 2025 · similarity 0.83)
- A Submodular Optimization Approach to Accountable Loan Approval (AAAI 2024 · similarity 0.82)
- Dynamic Graph Learning with Static Relations for Credit Risk Assessment (AAAI 2025 · similarity 0.82)
- Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum (AAAI 2024 · similarity 0.81)
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.