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. 数学与系统科学研究院
  3. 中国科学院数学与系统科学研究院
  4. 应用数学研究所
Deep graph level anomaly detection with contrastive learning

文献类型：期刊论文

作者Luo, Xuexiong1,2; Wu, Jia2; Yang, Jian2; Xue, Shan3; Peng, Hao4; Zhou, Chuan5; Chen, Hongyang1; Li, Zhao1,6; Sheng, Quan Z.2
刊名SCIENTIFIC REPORTS
出版日期2022-11-18
卷号12期号:1页码:11
ISSN号2045-2322
DOI10.1038/s41598-022-22086-3
英文摘要Graph level anomaly detection (GLAD) aims to spot anomalous graphs that structure pattern and feature information are different from most normal graphs in a graph set, which is rarely studied by other researchers but has significant application value. For instance, GLAD can be used to distinguish some different characteristic molecules in drug discovery and chemical analysis. However, GLAD mainly faces the following three challenges: (1) learning more comprehensive graph level representations to differ normal graphs and abnormal graphs, (2) designing an effective graph anomaly evaluation paradigm to capture graph anomalies from the local and global graph perspectives, (3) overcoming the number imbalance problem of normal and abnormal graphs. In this paper, we combine graph neural networks and contrastive learning to build an end-to-end GLAD framework for solving the three challenges above. We aim to design a new graph level anomaly evaluation way, which first utilizes the contrastive learning strategy to enhance different level representations of normal graphs from node and graph levels by a graph convolution autoencoder with perturbed graph encoder. Then, we evaluate the error of them with corresponding representations of the generated reconstruction graph to detect anomalous graphs. Extensive experiments on ten real-world datasets from three areas, such as molecular, protein and social network anomaly graphs, show that our model can effectively detect graph level anomaly from the majority and outperform existing advanced methods.
资助项目ARC DECRA Project[DE200100964] ; NSFC[61872360] ; NSFC[62271452] ; CAS Project for Young Scientists in Basic Research[YSBR-008] ; Key Research Project of Zhejiang Lab[2022PI0AC01] ; National Key R&D Program of China[2022YFB4500300]
WOS研究方向Science & Technology - Other Topics
语种英语
出版者NATURE PORTFOLIO
WOS记录号WOS:000885379900026
源URL[http://ir.amss.ac.cn/handle/2S8OKBNM/60655]  
专题应用数学研究所
通讯作者Wu, Jia
作者单位1.Zhejiang Lab, Hangzhou, Peoples R China
2.Macquarie Univ, Sch Comp, Sydney, NSW, Australia
3.Univ Wollongong, Sch Comp & Informat Technol, Wollongong, NSW, Australia
4.Beihang Univ, Beijing Adv Innovat Ctr Big Data & Brain Comp, Beijing, Peoples R China
5.Acad Math & Syst Sci, Chinese Acad Sci, Beijing, Peoples R China
6.Hangzhou Yugu Technol, Hangzhou, Peoples R China
推荐引用方式
GB/T 7714		 Luo, Xuexiong,Wu, Jia,Yang, Jian,et al. Deep graph level anomaly detection with contrastive learning[J]. SCIENTIFIC REPORTS,2022,12(1):11.
APA Luo, Xuexiong.,Wu, Jia.,Yang, Jian.,Xue, Shan.,Peng, Hao.,...&Sheng, Quan Z..(2022).Deep graph level anomaly detection with contrastive learning.SCIENTIFIC REPORTS,12(1),11.
MLA Luo, Xuexiong,et al."Deep graph level anomaly detection with contrastive learning".SCIENTIFIC REPORTS 12.1(2022):11.

入库方式： OAI收割

来源：数学与系统科学研究院

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。