Litcius/Paper detail

Spatial-Temporal-Aware Graph Transformer for Transaction Fraud Detection

Yue Tian, Guanjun Liu

2024IEEE Transactions on Industrial Informatics24 citationsDOI

Abstract

How to obtain informative representations of transactions and then perform the identification of fraudulent transactions is a crucial part of ensuring financial security. Recent studies apply graph neural networks (GNNs) to the transaction fraud detection problem. Nevertheless, they encounter challenges in effectively learning spatial-temporal information due to structural limitations. Moreover, few prior GNN-based detectors have recognized the significance of incorporating global information which encompasses similar behavioral patterns and offers valuable insights for discriminative representation learning. Therefore, we propose a novel heterogeneous GNN called Spatial-Temporal-Aware Graph Transformer (STA-GT) for transaction fraud detection problems. Specifically, we design a temporal encoding strategy to capture temporal dependencies and incorporate it into the GNN framework, enriching spatial-temporal information and improving expressive ability. Furthermore, we introduce a transformer module to learn local and global information. Pairwise node–node interactions overcome the limitation of the GNN structure and build up the interactions between a target node and many long-distance ones. Experimental results on two financial datasets demonstrate that our STA-GT is more effective on the transaction fraud detection task compared to general GNN models and GNN-based fraud detectors.

Topics & Concepts

Computer scienceTransaction processingDatabase transactionGraphData miningTheoretical computer scienceDatabaseImbalanced Data Classification TechniquesCybercrime and Law Enforcement Studies
Spatial-Temporal-Aware Graph Transformer for Transaction Fraud Detection | Litcius