ConFraudCLR-HeteroGNN-CCFD: Self-Supervised Contrastive Learning on Heterogeneous Graphs for Credit Card Fraud Detection
Abstract
A self-supervised contrastive learning framework using NT-Xent loss on heterogeneous graph neural networks for credit card fraud detection. The implementation features a two-stage pretrain-finetune pipeline with feature augmentation and optional SMOTE-based oversampling for handling class imbalance.
Fields of Study & Subjects
Advanced Graph Neural Networks
Imbalanced Data Classification Techniques
Privacy-Preserving Technologies in Data
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 16 February 2026
- Language
- EN