{"slug": "rgh-gnn-risk-gated-heterogeneous-graph-neural-network-for-financial-fraud", "title": "RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detection", "summary": "A new heterogeneous graph neural network called RGH-GNN achieved an AUC-ROC of 0.914 on the IEEE-CIS fraud detection dataset, outperforming all standard graph neural network baselines trained on the same heterogeneous graph across every evaluation metric, according to the arXiv paper 2610.27107v1. RGH-GNN uses transaction-level risk scores from a supervised LightGBM classifier as edge weights, feeding a learnable risk-gated aggregation mechanism so high-risk transactions contribute more strongly to learned representations instead of being diluted by uniform neighborhood aggregation. The authors frame the work as addressing class imbalance and camouflaged fraud in credit card transaction data, where shared accounts and devices create relational patterns that individual transaction features miss.", "body_md": "arXiv:2610.27107v1 Announce Type: new \nAbstract: Credit card fraud is a significant problem for financial institutions, resulting in substantial monetary loss each year. Fraud patterns and methods are continuously evolving, with fraudulent transactions often disguised to resemble legitimate activity. Real world transaction data for fraud detection is severely affected by class imbalance making it harder to detect these transactions. Fraudulent transactions are rarely isolated. Accounts, devices, and other common attributes are often shared across fraudulent activity, revealing relational patterns that individual transaction features alone cannot capture. Graph-based approaches model these relationships explicitly. However, standard graph neural networks aggregate neighbourhood information uniformly, which can dilute the already scarce signal carried by fraudulent transactions and limit detection of camouflaged fraud. This work presents RGH-GNN, a heterogeneous graph neural network that addresses this limitation by incorporating transaction-level risk scores, generated by a supervised LightGBM classifier as edge weights. It is used to guide message passing through a learnable risk-gated aggregation mechanism. It ensures that high-risk transactions contribute more strongly to learned representations rather than being diluted by uniform neighbourhood aggregation. RGH-GNN is evaluated on the IEEE-CIS fraud detection dataset against standard graph neural network models that are trained on the same heterogeneous graph. RGH-GNN outperforms all baselines across every evaluation metric, with an AUC-ROC score of 0.914. This demonstrates that incorporating engineered risk signals into graph-based message passing substantially improves fraud detection performance.", "url": "https://wpnews.pro/news/rgh-gnn-risk-gated-heterogeneous-graph-neural-network-for-financial-fraud", "canonical_source": "https://arxiv.org/abs/2610.27107", "published_at": "2026-10-21 04:00:00+00:00", "updated_at": "2026-10-21 04:21:33.358753+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "artificial-intelligence", "ai-research"], "entities": ["RGH-GNN", "LightGBM", "IEEE-CIS fraud detection dataset", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/rgh-gnn-risk-gated-heterogeneous-graph-neural-network-for-financial-fraud", "markdown": "https://wpnews.pro/news/rgh-gnn-risk-gated-heterogeneous-graph-neural-network-for-financial-fraud.md", "text": "https://wpnews.pro/news/rgh-gnn-risk-gated-heterogeneous-graph-neural-network-for-financial-fraud.txt", "jsonld": "https://wpnews.pro/news/rgh-gnn-risk-gated-heterogeneous-graph-neural-network-for-financial-fraud.jsonld"}}