A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection

TL;DR

This paper introduces HUGE, an unsupervised graph fraud detection method that leverages a novel label-free heterophily metric and an alignment-based detection module, effectively identifying fraudsters without labeled data.

Contribution

The paper proposes a novel unsupervised GFD approach with a new heterophily metric and an alignment-based detection architecture, addressing the challenge of detecting fraud without labels.

Findings

HUGE outperforms existing methods on 6 datasets.

The HALO metric accurately estimates heterophily from node attributes.

The alignment-based module enhances robustness and detection accuracy.

Abstract

Graph fraud detection (GFD) has rapidly advanced in protecting online services by identifying malicious fraudsters. Recent supervised GFD research highlights that heterophilic connections between fraudsters and users can greatly impact detection performance, since fraudsters tend to camouflage themselves by building more connections to benign users. Despite the promising performance of supervised GFD methods, the reliance on labels limits their applications to unsupervised scenarios; Additionally, accurately capturing complex and diverse heterophily patterns without labels poses a further challenge. To fill the gap, we propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD, which contains two essential components: a heterophily estimation module and an alignment-based fraud detection module. In the heterophily estimation module, we design a novel label-free heterophily metric called HALO, which captures the critical graph properties for GFD, enabling its outstanding ability to estimate heterophily from node attributes. In the alignment-based fraud detection module, we develop a joint MLP-GNN architecture with ranking loss and asymmetric alignment loss. The ranking loss aligns the predicted fraud score with the relative order of HALO, providing an extra robustness guarantee by comparing heterophily among non-adjacent nodes. Moreover, the asymmetric alignment loss effectively utilizes structural information while alleviating the feature-smooth effects of GNNs. Extensive experiments on 6 datasets demonstrate that HUGE significantly outperforms competitors, showcasing its effectiveness and robustness.