Dual-channel Heterophilic Message Passing for Graph Fraud Detection
This work addresses fraud detection in domains like e-commerce and social networks, offering a novel method to handle heterophily in graphs, though it is incremental in advancing GNN-based fraud detection techniques.
The paper tackles the problem of fraud detection in graphs by addressing the limitations of existing GNN methods that exclude heterophilic neighbors, which disrupts graph topology and increases prediction uncertainty. It proposes DHMP, a framework that separates homophilic and heterophilic subgraphs, achieving improved performance as demonstrated by outperforming existing methods on three real-world datasets.
Fraudulent activities have significantly increased across various domains, such as e-commerce, online review platforms, and social networks, making fraud detection a critical task. Spatial Graph Neural Networks (GNNs) have been successfully applied to fraud detection tasks due to their strong inductive learning capabilities. However, existing spatial GNN-based methods often enhance the graph structure by excluding heterophilic neighbors during message passing to align with the homophilic bias of GNNs. Unfortunately, this approach can disrupt the original graph topology and increase uncertainty in predictions. To address these limitations, this paper proposes a novel framework, Dual-channel Heterophilic Message Passing (DHMP), for fraud detection. DHMP leverages a heterophily separation module to divide the graph into homophilic and heterophilic subgraphs, mitigating the low-pass inductive bias of traditional GNNs. It then applies shared weights to capture signals at different frequencies independently and incorporates a customized sampling strategy for training. This allows nodes to adaptively balance the contributions of various signals based on their labels. Extensive experiments on three real-world datasets demonstrate that DHMP outperforms existing methods, highlighting the importance of separating signals with different frequencies for improved fraud detection. The code is available at https://github.com/shaieesss/DHMP.