Addressing Noise and Stochasticity in Fraud Detection for Service Networks

2025-05-02

AI Summary

Addressing two key challenges in service network fraud detection—graph signal corruption by propagation noise and distortion in frequency-domain feature fusion—this paper proposes SGNN-IB, a spectral graph neural network grounded in information bottleneck (IB) theory. Methodologically, it pioneers the coupling of IB with prototype learning, enabling frequency-domain decoupling via homophilous/heterophilous subgraph decomposition: during encoding, redundant information is compressed to enhance discriminability; during fusion, frequency fidelity is preserved to mitigate distortion. Evaluated on three real-world service network datasets, SGNN-IB consistently outperforms state-of-the-art methods, achieving an average 3.2% improvement in fraud detection accuracy and markedly enhanced noise robustness. Its core contribution lies in the first integration of the information bottleneck principle into the spectral graph filtering framework, thereby jointly optimizing noise robustness and frequency-domain interpretability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Fraud detection is crucial in social service networks to maintain user trust and improve service network security. Existing spectral graph-based methods address this challenge by leveraging different graph filters to capture signals with different frequencies in service networks. However, most graph filter-based methods struggle with deriving clean and discriminative graph signals. On the one hand, they overlook the noise in the information propagation process, resulting in degradation of filtering ability. On the other hand, they fail to discriminate the frequency-specific characteristics of graph signals, leading to distortion of signals fusion. To address these issues, we develop a novel spectral graph network based on information bottleneck theory (SGNN-IB) for fraud detection in service networks. SGNN-IB splits the original graph into homophilic and heterophilic subgraphs to better capture the signals at different frequencies. For the first limitation, SGNN-IB applies information bottleneck theory to extract key characteristics of encoded representations. For the second limitation, SGNN-IB introduces prototype learning to implement signal fusion, preserving the frequency-specific characteristics of signals. Extensive experiments on three real-world datasets demonstrate that SGNN-IB outperforms state-of-the-art fraud detection methods.

Problem

• Improving fraud detection accuracy in service networks
• Reducing noise in graph signal propagation
• Preserving frequency-specific signal characteristics

Innovation

• Splits graph into homophilic and heterophilic subgraphs
• Applies information bottleneck for key characteristics
• Uses prototype learning for signal fusion