Two-stage GNN-based fraud detection with camouflage identification and enhanced semantics aggregation

Abstract

Graph neural network (GNN) has got lots of attention recently in the fraud detection task due to its message-passing mechanism, which can aggregate neighbors feature in the information network. While promising, currently most GNN-based fraud detectors fail to identify camouflage caused by fraud with graph structure information and embed entity in deep layer with rich semantics effectively. To solve these problems, we propose a two-stage GNN-based approach with camouflage identification and enhanced semantics aggregation (CIES-GNN) for fraud detection. In the proposed approach, camouflage is identified by reconstructing subgraphs with both node feature and structure information. Detailedly, hidden edges between fraudsters are found by reconstructing a dense subgraph of fraudster nodes, and redundant connections between benign nodes and fraudster nodes are eliminated by reconstructing subgraphs in a label-balance distribution. Moreover, to embed entity in deep layer without semantics obfuscation, the node information is embedded in an enhanced semantics aggregation module, which fuses higher-order information in intra-relation and aggregates semantics in inter-relation respectively. Experiments on two real-world datasets demonstrate that the proposed CIES-GNN outperforms state-of-the-art baselines.