Dual-channel Heterophilic Message Passing for Graph Fraud Detection

2025-04-19

AI Summary

Existing spatial Graph Neural Network (GNN)-based fraud detection methods often prune heterogeneous neighbors to satisfy the homophily assumption, leading to graph topology distortion and increased prediction uncertainty. To address this, we propose the Dual-channel Heterogeneity-aware Message Passing (DHMP) framework—the first GNN architecture to explicitly decouple homogeneous and heterogeneous subgraphs. DHMP introduces a heterogeneity separation module, a shared-weight dual-channel message propagation mechanism, and a label-aware adaptive sampling strategy, enabling independent modeling and dynamic fusion of multi-frequency signals. Crucially, DHMP preserves the original graph structure while significantly enhancing discriminative capability for heterogeneous fraud patterns. Extensive experiments on three real-world e-commerce and social network fraud datasets demonstrate that DHMP consistently outperforms state-of-the-art methods, validating the critical importance of explicit heterogeneity modeling for both detection accuracy and robustness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• Detect fraud in heterophilic graphs without disrupting topology
• Balance homophilic and heterophilic signals for accurate predictions
• Improve GNN performance by separating frequency-based graph signals

Innovation

• Dual-channel heterophilic message passing framework
• Heterophily separation module divides graph
• Customized sampling strategy for training