中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
Multipattern Integrated Networks With Contrastive Pretraining for Graph Anomaly Detection

文献类型：期刊论文

作者Yang, Manzhi1; Zhang, Jian2; Lin, Liyuan2; Han, Jinpeng3; Chen, Xiaoguang1; Wang, Zhen4,5; Wang, Fei-Yue1,6,7,8
刊名IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
出版日期2024-07-19
页码12
关键词Fraud Contrastive learning Representation learning Telecommunications Credit cards Collaboration Task analysis Anomaly detection contrastive learning graph neural network network representation learning
ISSN号2329-924X
DOI10.1109/TCSS.2024.3362393
通讯作者Wang, Fei-Yue(feiyue.wang@ia.ac.cn)
英文摘要As a challenge of practical significance, fraud detection has great potential for telecom fraud prevention, economic crime prevention, and personal property preservation. Fraudulent activities are always buried in massive regular transactions, making it hard to find them. Traditional rule-based approaches need multiple domain-specific rules and multistep verification, which limits their transferability and efficiency. Machine learning-based methods might ignore the intricate interactions or the temporal relations among accounts. Meanwhile, the lack of sufficient manual labels restricts their performance. To overcome the above limitations, we present a multipattern integrated network (MPIN) in this article to identify fraudulent accounts in transaction networks. Specifically, MPIN considers the interactions among nodes from three perspectives: inflows, outflows, and their mutual influences. To learn the behavior pattern of each node, MPIN first applies an attention mechanism to integrate the short-term information and then learns the long-term patterns by aggregating multiple short-term patterns. Behavior patterns from different perspectives together with long short-term modeling enable the model to precisely distinguish fraudulent accounts from the normal ones. Moreover, contrastive pretraining with temporal consistency and local tightness guarantee is adopted to alleviate the label sparsity issue and provide the model with low-variance performance. We conducted experiments on two real-world transaction networks, and the results showed the effectiveness of MPIN compared with five state-of-the-art baselines.
WOS关键词MACHINES
资助项目Science and Technology Development Fund, Macao SAR[0093/2023/RIA2] ; National Natural Science Foundation of China[62176080]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001273025600001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Science and Technology Development Fund, Macao SAR ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/59349]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Wang, Fei-Yue
作者单位1.Macau Univ Sci & Technol, Macau Inst Syst Engn, Macau 999078, Peoples R China
2.Hangzhou Dianzi Univ, Sch Cyberspace, Hangzhou 310000, Peoples R China
3.Xi An Jiao Tong Univ, Sch Software Engn, Xian 710049, Peoples R China
4.Hangzhou Dianzi Univ, Sch Cyberspace, Hangzhou 310000, Peoples R China
5.Hangzhou Dianzi Univ, Expt Ctr Data Sci & Intelligent Decis Making, Hangzhou 310000, Peoples R China
6.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
7.Chinese Acad Sci, Beijing Engn Res Ctr Intelligent Syst & Technol, Beijing 100190, Peoples R China
8.Beijing Huairou Acad Parallel Sensing, Beijing 101407, Peoples R China
推荐引用方式
GB/T 7714		 Yang, Manzhi,Zhang, Jian,Lin, Liyuan,et al. Multipattern Integrated Networks With Contrastive Pretraining for Graph Anomaly Detection[J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,2024:12.
APA Yang, Manzhi.,Zhang, Jian.,Lin, Liyuan.,Han, Jinpeng.,Chen, Xiaoguang.,...&Wang, Fei-Yue.(2024).Multipattern Integrated Networks With Contrastive Pretraining for Graph Anomaly Detection.IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,12.
MLA Yang, Manzhi,et al."Multipattern Integrated Networks With Contrastive Pretraining for Graph Anomaly Detection".IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2024):12.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。