A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection
Date
2025
Authors
Pan, J.
Liu, Y.
Zheng, X.
Zheng, Y.
Liew, A.W.C.
Li, F.
Pan, S.
Editors
Walsh, T.
Shah, J.
Kolter, Z.
Shah, J.
Kolter, Z.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI-25), 2025 / Walsh, T., Shah, J., Kolter, Z. (ed./s), vol.39, iss.12, pp.12443-12451
Statement of Responsibility
Junjun Pan, Yixin Liu, Xin Zheng, Yizhen Zheng, Alan Wee-Chung Liew, Fuyi Li, Shirui Pan
Conference Name
39th Annual AAAI Conference on Artificial Intelligence (AAAI) (25 Feb 2025 - 4 Mar 2025 : Philadelphia, Pennsylvania)
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 fraudster and user greatly impacts detection performance, where the fraudsters tend to camouflage themselves by building more connections to benign users. Despite their promising performance, their label reliance limits its application in unsupervised scenarios; Additionally, accurately capturing complex and diverse heterophily patterns without labels poses a further challenge. Therefore, 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 unsupervised heterophily metric called HALO, which captures the critical graph properties for GFD, enabling its outstanding ability to estimate heterophily with 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 between non-adjacent nodes. Moreover, the asymmetric alignment loss effectively utilizes structural information to alleviate the feature-smooth effects. Extensive experiments on six datasets demonstrate that HUGE consistently outperforms competitors, showcasing its effectiveness and robustness.
School/Discipline
Dissertation Note
Provenance
Description
Technical Tracks 12
AAAI Technical Track on Data Mining & Knowledge Management II
Access Status
Rights
© 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.