Graph-Based Fraud Detection with Dual-Path Graph Filtering

arXiv cs.LG / 4/17/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper tackles fraud detection on graph-structured data, arguing that common GNN approaches struggle due to relation camouflage, strong heterophily, and class imbalance in real fraud graphs.
It introduces DPF-GFD, which uses a beta wavelet-based operator to extract structural patterns from the original graph before building a similarity graph from distance-based node representations.
The method applies an improved low-pass filter to the similarity graph and then fuses embeddings from both paths via supervised representation learning to produce more discriminative node features.
An ensemble tree model uses the learned node features to estimate fraud risk for unlabeled nodes, and experiments on four real-world financial fraud datasets show improved effectiveness.
The key novelty is a frequency-complementary dual-path filtering framework that explicitly separates structural anomaly modeling from feature similarity modeling, improving stability under challenging graph conditions.

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.