Modelling graph dynamics in fraud detection with "Attention"
This addresses fraud detection for online retail platforms, presenting an incremental improvement by adapting attention mechanisms to dynamic heterogeneous graphs.
The paper tackled fraud detection on online retail platforms by proposing DyHGN models to handle dynamic heterogeneous graphs, achieving improved detection performance with concrete metrics on eBay data.
At online retail platforms, detecting fraudulent accounts and transactions is crucial to improve customer experience, minimize loss, and avoid unauthorized transactions. Despite the variety of different models for deep learning on graphs, few approaches have been proposed for dealing with graphs that are both heterogeneous and dynamic. In this paper, we propose DyHGN (Dynamic Heterogeneous Graph Neural Network) and its variants to capture both temporal and heterogeneous information. We first construct dynamic heterogeneous graphs from registration and transaction data from eBay. Then, we build models with diachronic entity embedding and heterogeneous graph transformer. We also use model explainability techniques to understand the behaviors of DyHGN-* models. Our findings reveal that modelling graph dynamics with heterogeneous inputs need to be conducted with "attention" depending on the data structure, distribution, and computation cost.