Multi-Temporal Partitioned Graph Attention Networks for Financial Fraud Detection

The issue of transaction security has attracted widespread attention due to the frequent occurrence of financial fraud. Graph neural networks (GNNs) can effectively detect financial fraudulent behavior by capturing transaction relationships. However, many existing methods lack the consideration of modeling user behavior patterns at diverse timescales. Moreover, GNN-based approaches usually fail to adaptively perceive neighborhood information from global and local perspectives, resulting in some transaction node embeddings merging the information from partially irrelevant neighboring transaction nodes and leading to suboptimal performance. Therefore, this work proposes a Multi-Temporal Partitioned graph attention Network (MTPNet) for financial fraud detection. In particular, we design a multi-temporal partitioned graph construction algorithm that generates multi-temporal series graphs at various timescales. These graphs effectively express the periodic variations in users’ transaction behavior pattern, allowing GNNs to learn knowledge from these graphs and extract richer semantic information. Then, we propose a global-local neighborhood-aware encoder to enable transaction node embeddings to adaptively aggregate their most relevant neighborhood information based on the attention mechanism. We perform extensive experiments to evaluate the performance of MTPNet on large-scale financial fraud datasets and demonstrate its effectiveness.