Barely Supervised Learning for Graph-Based Fraud Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (15) · 16548-16557
DOI: 10.1609/aaai.v38i15.29593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Hang Yu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref).
Abstract (Originalsprache)
In recent years, graph-based fraud detection methods have garnered increasing attention for their superior ability to tackle the issue of camouflage in fraudulent scenarios. However, these methods often rely on a substantial proportion of samples as the training set, disregarding the reality of scarce annotated samples in real-life scenarios. As a theoretical framework within semi-supervised learning, the principle of consistency regularization posits that unlabeled samples should be classified into the same category as their own perturbations. Inspired by this principle, this study incorporates unlabeled samples as an auxiliary during model training, designing a novel barely supervised learning method to address the challenge of limited annotated samples in fraud detection. Specifically, to tackle the issue of camouflage in fraudulent scenarios, we employ disentangled representation learning based on edge information for a small subset of annotated nodes. This approach partitions node features into three distinct components representing different connected edges, providing a foundation for the subsequent augmentation of unlabeled samples. For the unlabeled nodes used in auxiliary training, we apply both strong and weak augmentation and design regularization losses to enhance the detection performance of the model in the context of extremely limited labeled samples. Across five publicly available datasets, the proposed model showcases its superior detection capability over baseline models.
Zitieren
APA
Yu, H., Liu, Z., & Luo, X. (2024). Barely Supervised Learning for Graph-Based Fraud Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(15), 16548-16557. https://doi.org/10.1609/aaai.v38i15.29593
Vancouver
Yu H, Liu Z, Luo X. Barely Supervised Learning for Graph-Based Fraud Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(15):16548-16557. doi:10.1609/aaai.v38i15.29593
BibTeX
@article{Yu2024,
author = {Yu, Hang and Liu, Zhengyang and Luo, Xiangfeng},
title = {Barely Supervised Learning for Graph-Based Fraud Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {15},
pages = {16548--16557},
doi = {10.1609/aaai.v38i15.29593}
}
EUVIMED