RWK-GNN：基于特征增强与子核分解的非平衡图欺诈检测算法

于浩淼; 刘炜; 孟流畅; 陈开睿; 宋友

doi:10.12263/DZXB.20240346

您当前的位置：

首页 >

文章列表页 >

RWK-GNN：基于特征增强与子核分解的非平衡图欺诈检测算法

学术论文 | 更新时间：2026-05-07

- RWK-GNN：基于特征增强与子核分解的非平衡图欺诈检测算法
- RWK-GNN: Fraud Detection for Imbalanced Graphs with Feature Enhancement and Subkernel Decomposition
- 电子学报 2024年52卷第10期页码：3382-3391
- 作者机构：
  
  北京航空航天大学软件学院，北京 100191
- 作者简介：
  
  [ "于浩淼男，2000年3月出生于河南省周口市.现为北京航空航天大学软件学院硕士研究生.主要研究方向为图神经网络与欺诈检测.E-mail: yuhaomiao@buaa.edu.cn" ]
  [ "刘炜男，1998年12月出生于内蒙古自治区呼和浩特市，现为北京航空航天大学软件学院硕士研究生，主要研究方向为图神经网络、机器学习与欺诈检测等.E-mail: buaaliuwei@buaa.edu.cn" ]
  [ "孟流畅女，2002年4月出生于山东省德州市，现为北京航空航天大学软件学院硕士研究生，主要研究方向为射电望远镜数据处理、图像处理、图神经网络等.E-mail: SY2321112@buaa.edu.cn" ]
  [ "陈开睿男，2000年8月出生于广东省珠海市，现为北京航空航天大学软件学院硕士研究生，主要研究方向为智能软件工程、代码翻译、持续学习等.E-mail: SY2221103@buaa.edu.cn" ]
  [ "宋友男，1973年8月出生于四川省乐山市.现为北京航空航天大学软件学院教授、博士生导师.主要研究方向为大数据分析、人机交互、科技金融、人工智能等.中国电子学会会员编号：E190161439M.E-mail: songyou@buaa.edu.cn" ]
- 基金信息：
  
  河北省重点研发计划(21310101D)
- DOI：10.12263/DZXB.20240346
  中图分类号： TP311.5;TP391.4
- 收稿：2024-04-17，
  
  修回：2024-08-26，
  
  纸质出版：2024-10-25
- 稿件说明：
移动端阅览
于浩淼, 刘炜, 孟流畅, 等. RWK-GNN：基于特征增强与子核分解的非平衡图欺诈检测算法[J]. 电子学报, 2024, 52(10): 3382-3391.

YU Hao-miao, LIU Wei, MENG Liu-chang, et al. RWK-GNN: Fraud Detection for Imbalanced Graphs with Feature Enhancement and Subkernel Decomposition[J]. Acta Electronica Sinica, 2024, 52(10): 3382-3391.
于浩淼, 刘炜, 孟流畅, 等. RWK-GNN：基于特征增强与子核分解的非平衡图欺诈检测算法[J]. 电子学报, 2024, 52(10): 3382-3391. DOI：10.12263/DZXB.20240346

YU Hao-miao, LIU Wei, MENG Liu-chang, et al. RWK-GNN: Fraud Detection for Imbalanced Graphs with Feature Enhancement and Subkernel Decomposition[J]. Acta Electronica Sinica, 2024, 52(10): 3382-3391. DOI：10.12263/DZXB.20240346

摘要

金融欺诈对经济和社会稳定造成了严重的威胁，因此开发有效的欺诈检测算法对于保护金融系统的完整性至关重要.目前已有多种基于图学习的欺诈检测算法应用于实际场景当中，这些方法或针对图的结构信息开展分类，或通过图卷积神经网络学习节点的嵌入式表示进行欺诈检测工作，关注角度相对单一，无法完备地在非平衡多关系图上开展欺诈检测分析.针对以上问题，本论文提出了一种结合随机游走下的特征增强与子核分解的图神经网络欺诈检测算法（Random Walk feature enhancement and Kcore subkernel decomposition Graph Neural Network，RWK-GNN），该算法能够高效地挖掘出多关系不平衡图中节点层级与全局网络层级的拓扑信息，并通过子核分解算法优化图结构特征在社区演进角度上的传播与聚合，最终完成欺诈检测与识别.为验证RWK-GNN算法性能，本文使用了图神经网络欺诈检测任务常用的公开数据集进行模型训练与测试.实验结果表明，在同一评价指标下，该方法较相关机器学习算法与图神经网络算法有着较大提升，与CARE-GNN算法相比，该方法的AUC值提升了17%；与PC-GNN算法相比，该方法的AUC值提升了8%；与SIGN算法相比，该方法的AUC值提升了7%.

Abstract

Financial fraud poses a serious threat to the economic and social stability

making the development of effective fraud detection algorithms crucial for safeguarding the integrity of the financial system. Currently

various graph-based fraud detection algorithms have been applied in practical scenarios. These methods either classify based on the structural information of graphs or utilize graph convolutional neural networks to learn embedded representations of nodes for fraud detection. However

these approaches have relatively narrow perspectives and cannot comprehensively analyze fraud detection on imbalanced multi-relational graphs. To address these issues

this paper proposes a RWK-GNN (Random Walk feature enhancement and Kcore subkernel decomposition Graph Neural Network)

which efficiently extracts topological information at both the node level and the global network level in imbalanced graphs with multiple relationships. It optimizes the propagation and aggregation of graph structural features from the perspective of community evolution through subkernel decomposition algorithm

ultimately achieving fraud detection and identification. To validate the performance of the RWK-GNN algorithm

this study employs commonly used public datasets for graph neural network fraud detection tasks in model training and testing. Experimental results demonstrate significant improvements of this method over other machine learning algorithms and graph neural network algorithms in terms of the same evaluation metrics. Compared to the CARE-GNN algorithm

the proposed method achieves a 17% increase in AUC value. Compared to the PC-GNN algorithm

the proposed method achieves an 8% increase in AUC value. Moreover

compared to the SIGN algorithm

the proposed method achieves a 7% increase in AUC value.

关键词

Keywords

references

北京金融信息化研究所 . 金融反欺诈与大数据风控研究报告 [EB/OL ] . ( 2023-12-26 )[ 2024-04-10 ] . https://www.docin.com/p-4571244234.html https://www.docin.com/p-4571244234.html .

MOTIE S , RAAHEMI B . Financial fraud detection using graph neural networks: A systematic review [J ] . Expert Systems with Applications , 2024 , 240 : 122156 .

PORTER D . Reusable analysis and design components for knowledge-based system development [M ] // Lecture Notes in Computer Science . Berlin, Heidelberg : Springer Berlin Heidelberg , 1992 : 373 - 391 .

VATSA V , SURAL S , MAJUMDAR A K . A game-theoretic approach to credit card fraud detection [M ] // Lecture Notes in Computer Science . Berlin : Springer Berlin Heidelberg , 2005 : 263 - 276 .

LIU D , GU T , XUE J P . Rule engine based on improvement rete algorithm [C ] // The 2010 International Conference on Apperceiving Computing and Intelligence Analysis Proceeding . Piscataway : IEEE , 2010 : 346 - 349 .

GIANINI G , FOSSI L G , MIO C , et al . Managing a pool of rules for credit card fraud detection by a Game Theory based approach [J ] . Future Generation Computer Systems , 2020 , 102 : 549 - 561 .

ABDALLAH A , MAAROF M A , ZAINAL A . Fraud detection system: A survey [J ] . Journal of Network and Computer Applications , 2016 , 68 : 90 - 113 .

KOKKINAKI A I . On atypical database transactions: identification of probable frauds using machine learning for user profiling [C ] // Proceedings 1997 IEEE Knowledge and Data Engineering Exchange Workshop . Piscataway : IEEE , 1997 : 107 - 113 .

SOEMERS D , BRYS T , DRIESSENS K , et al . Adapting to concept drift in credit card transaction data streams using contextual bandits and decision trees [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2018 , 32 ( 1 ): 7831 - 7836 .

LIU Z Q , CHEN C C , YANG X X , et al . Heterogeneous graph neural networks for malicious account detection [C ] // Proceedings of the 27th ACM International Conference on Information and Knowledge Management . New York : ACM , 2018 : 2077 - 2085 .

WANG D X , LIN J B , CUI P , et al . A semi-supervised graph attentive network for financial fraud detection [C ] // 2019 IEEE International Conference on Data Mining (ICDM) . Piscataway : IEEE , 2019 : 598 - 607 .

LIU Z W , DOU Y T , YU P S , et al . Alleviating the inconsistency problem of applying graph neural network to fraud detection [C ] // Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2020 : 1569 - 1572 .

李康和 , 黄震华 . 基于噪声过滤与特征增强的图神经网络欺诈检测方法 [J ] . 电子学报 , 2023 , 51 ( 11 ): 3053 - 3060 .

LI K H , HUANG Z H . Noise filtering and feature enhancement based graph neural network method for fraud detection [J ] . Acta Electronica Sinica , 2023 , 51 ( 11 ): 3053 - 3060 . (in Chinese)

PEROZZI B , AL-RFOU R , SKIENA S . DeepWalk: Online learning of social representations [C ] // Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2014 : 701 - 710 .

GROVER A , LESKOVEC J . Node2vec: Scalable feature learning for networks [J ] . KDD: Proceedings. International Conference on Knowledge Discovery & Data Mining , 2016 , 2016 : 855 - 864 .

RIBEIRO L F R , SAVERESE P H P , FIGUEIREDO D R . Struc2vec: Learning node representations from structural identity [C ] // Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2017 : 385 - 394 .

PEDREGOSA F , VAROQUAUX G , GRAMFORT A , et al . Scikit-learn: Machine learning in Python [EB/OL ] . ( 2012-01-02 )[ 2024-04-10 ] . https://arxiv.org/abs/1201.0490 https://arxiv.org/abs/1201.0490 .

RAYANA S , AKOGLU L . Collective opinion spam detection: Bridging review networks and metadata [C ] // Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2015 : 985 - 994 .

WU B , YAO X Y , ZHANG B Y , et al . SplitGNN: Spectral graph neural network for fraud detection against heterophily [C ] // Proceedings of the 32nd ACM International Conference on Information and Knowledge Management . New York : ACM , 2023 : 2737 - 2746 .

HAMILTON W L , YING R , LESKOVEC J . Inductive representation learning on large graphs [EB/OL ] . ( 2017-06-07 )[ 2024-04-10 ] . http://arxiv.org/abs/1706.02216 http://arxiv.org/abs/1706.02216

DOU Y T , LIU Z W , SUN L , et al . Enhancing graph neural network-based fraud detectors against camouflaged fraudsters [C ] // Proceedings of the 29th ACM International Conference on Information & Knowledge Management . New York : ACM , 2020 : 315 - 324

LIU Y , AO X , QIN Z D , et al . Pick and choose: A GNN-based imbalanced learning approach for fraud detection [C ] // Proceedings of the Web Conference 2021 . New York : ACM , 2021 : 3168 - 3177 .

SUN C , GU H , HU J . Scalable and adaptive graph neural networks with self-label-enhanced training [EB/OL ] . ( 2021-04-19 )[ 2024-04-10 ] . https://arxiv.org/abs/2104.09376 https://arxiv.org/abs/2104.09376 .

FRASCA F , ROSSI E , EYNARD D , et al . SIGN: Scalable inception graph neural networks [EB/OL ] . ( 2020-04-23 )[ 2024-04-10 ] . https://arxiv.org/abs/2004.11198 https://arxiv.org/abs/2004.11198 .

LI Q T , HE Y S , XU C , et al . Dual-augment graph neural network for fraud detection [C ] // Proceedings of the 31st ACM International Conference on Information & Knowledge Management . New York : ACM , 2022 : 4188 - 4192 .

HUANG M , LIU Y , AO X , et al . Auc-oriented graph neural network for fraud detection [C ] // Proceedings of the ACM Web Conference 2022 . New York : ACM , 2022 : 1311 - 1321 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于噪声过滤与特征增强的图神经网络欺诈检测方法

基于图神经网络的高光谱图像分类研究进展