Enhanced Pre-Trained Graph Neural Networks with Applications in Financial Fraud Detection

Graph Neural Networks (GNNs) have demonstrated strong potentials in identifying complex patterns and detecting anomalies in large data. While pre-training has proven highly effective in domains such as natural language processing and computer vision, its application in graph-based tasks remains under-explored due to the risk of negative transfer. In the context of GNNs, pre-training helps capture general graph-based relational patterns, enhancing performance in downstream tasks such as fraud detection by fine-tuning on a domain-specific dataset. This research explores how pre-training can enhance the performance of GNNs first by proposing a modular framework, which provides flexibility to experiment with different configurations. The proposed framework aims to systematically integrate configurable modules for dataset selection, pre-training task design, and model configuration. Second, to demonstrate the effectiveness of pre-training in graph-based data analysis, we pre-train a model on a large available dataset, then employ it for fraud detection in finance domain where availability of data could be limited. We perform an experiment leveraging the large DGraphFin dataset for pre-training, and the Elliptic dataset for fine-tuning. The pre-trained GNN achieves notable performance improvements, with an F1 score of 88.7% and a recall of 0.831, surpassing prior benchmarks. The findings affirm the transformative potential of pre-training in graph-based tasks, particularly in financial fraud detection. Pre-training enhanced both the accuracy and robustness of fraud detection models, making it a worthwhile approach to explore for addressing the challenges of real-world financial fraud.