Graph-Based Fraud Detection with Dual-Path Graph Filtering

2026-04-14

AI Summary

This work addresses the challenges of node-level fraud detection in graph-structured data, where relational camouflage, high heterophily, and class imbalance severely hinder performance. To tackle these issues, the authors propose DPF-GFD, a novel model that introduces a dual-path graph filtering paradigm with complementary frequency responses. The approach explicitly decouples structural anomaly modeling and feature similarity modeling by performing filtering on both the original graph and a similarity graph constructed based on node distances. By fusing embeddings from both paths, the model enhances representational discriminability and stability. Integrating Beta wavelet operators, an improved low-pass filter, supervised representation learning, and ensemble tree models, DPF-GFD significantly outperforms existing single-graph smoothing methods across four real-world financial fraud datasets.

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 embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Fraud detection on graph data can be viewed as a demanding task that requires distinguishing between different types of nodes. Because graph neural networks (GNNs) are naturally suited for processing information encoded in graph form through their message-passing operations, methods based on GNN models have increasingly attracted attention in the fraud detection domain. However, fraud graphs inherently exhibit relation camouflage, high heterophily, and class imbalance, causing most GNNs to underperform in fraud detection tasks. To address these challenges, this paper proposes a Graph-Based Fraud Detection Model with Dual-Path Graph Filtering (DPF-GFD). DPF-GFD first applies a beta wavelet-based operator to the original graph to capture key structural patterns. It then constructs a similarity graph from distance-based node representations and applies an improved low-pass filter. The embeddings from the original and similarity graphs are fused through supervised representation learning to obtain node features, which are finally used by an ensemble tree model to assess the fraud risk of unlabeled nodes. Unlike existing single-graph smoothing approaches, DPF-GFD introduces a frequency-complementary dual-path filtering paradigm tailored for fraud detection, explicitly decoupling structural anomaly modeling and feature similarity modeling. This design enables more discriminative and stable node representations in highly heterophilous and imbalanced fraud graphs. Comprehensive experiments on four real-world financial fraud detection datasets demonstrate the effectiveness of our proposed method.

Problem

• fraud detection
• graph neural networks
• heterophily
• class imbalance
• relation camouflage

Innovation

• dual-path graph filtering
• graph neural networks
• heterophily
• fraud detection
• graph signal processing