GraphGuard: Contrastive Self-Supervised Learning for Credit-Card Fraud Detection in Multi-Relational Dynamic Graphs
This addresses fraud detection for financial institutions, but it appears incremental as it builds on existing graph-based self-supervised methods.
The paper tackled credit card fraud detection by proposing GraphGuard, a contrastive self-supervised graph-based framework, and tested it on real-world and synthetic datasets, showing promising initial results.
Credit card fraud has significant implications at both an individual and societal level, making effective prevention essential. Current methods rely heavily on feature engineering and labeled information, both of which have significant limitations. In this work, we present GraphGuard, a novel contrastive self-supervised graph-based framework for detecting fraudulent credit card transactions. We conduct experiments on a real-world dataset and a synthetic dataset. Our results provide a promising initial direction for exploring the effectiveness of graph-based self-supervised approaches for credit card fraud detection.