Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance

Bin Wu, Kuo-Ming Chao, Yinsheng Li

Abstract: Highlights•Financial fraud is identified based on multiple views in supply chain finance.•A multitask learning framework with heterogeneous GNN is proposed to identify frauds.•Comprehensive explanations are provided on multiple heterogeneous graphs.•Experiments on five datasets show the effectiveness over state-of-the-art methods.