CSpace  > 应用数学研究所
Deep graph level anomaly detection with contrastive learning
Luo, Xuexiong1,5; Wu, Jia1; Yang, Jian1; Xue, Shan2; Peng, Hao3; Zhou, Chuan4; Chen, Hongyang5; Li, Zhao5,6; Sheng, Quan Z.1
AbstractGraph 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.
Indexed BySCI
Funding ProjectARC 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 Research AreaScience & Technology - Other Topics
WOS SubjectMultidisciplinary Sciences
WOS IDWOS:000885379900026
Citation statistics
Document Type期刊论文
Corresponding AuthorWu, Jia
Affiliation1.Macquarie Univ, Sch Comp, Sydney, NSW, Australia
2.Univ Wollongong, Sch Comp & Informat Technol, Wollongong, NSW, Australia
3.Beihang Univ, Beijing Adv Innovat Ctr Big Data & Brain Comp, Beijing, Peoples R China
4.Acad Math & Syst Sci, Chinese Acad Sci, Beijing, Peoples R China
5.Zhejiang Lab, Hangzhou, Peoples R China
6.Hangzhou Yugu Technol, Hangzhou, Peoples R China
Recommended Citation
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.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Luo, Xuexiong]'s Articles
[Wu, Jia]'s Articles
[Yang, Jian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Luo, Xuexiong]'s Articles
[Wu, Jia]'s Articles
[Yang, Jian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Luo, Xuexiong]'s Articles
[Wu, Jia]'s Articles
[Yang, Jian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.