CASIA OpenIR  > 模式识别国家重点实验室  > 智能交互
Self-supervised graph representation learning via bootstrapping
Che, Feihu1,2; Yang, Guohua1; Zhang, Dawei1; Tao, Jianhua1,2,3; Liu, Tong1
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2021-10-07
Volume456Pages:88-96
Abstract

Graph neural networks (GNNs) apply deep learning techniques to graph-structured data and have achieved promising performance in graph representation learning. However, existing GNNs rely heavily on labeled data or well-designed negative samples. To address these issues, we propose a new self-supervised graph representation method: deep graph bootstrapping (DGB). DGB consists of two neural networks: online and target networks, and the input of them are different augmented views of the initial graph. The online network is trained to predict the target network while the target network is updated with a slow-moving average of the online network, which means the online and target networks can learn from each other. As a result, the proposed DGB can learn graph representation without negative examples in an unsupervised manner. In addition, we summarize three kinds of augmentation methods for graph-structured data and apply them to the DGB. Experiments on the benchmark datasets show the DGB performs better than the current state-of-the-art methods and how the augmentation methods affect the performances. (c) 2021 Elsevier B.V. All rights reserved.

KeywordGraph representation learning Self-supervised Bootstrapping Graph neural network
DOI10.1016/j.neucom.2021.03.123
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Develop ment Plan of China[2018YFB1005003] ; National Natural Science Foundation of China (NSFC)[61831022] ; National Natural Science Foundation of China (NSFC)[61901473] ; National Natural Science Foundation of China (NSFC)[61771472] ; National Natural Science Foundation of China (NSFC)[61773379]
Funding OrganizationNational Key Research and Develop ment Plan of China ; National Natural Science Foundation of China (NSFC)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000687471900008
PublisherELSEVIER
Sub direction classification知识表示与推理
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/45912
Collection模式识别国家重点实验室_智能交互
Corresponding AuthorTao, Jianhua
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Che, Feihu,Yang, Guohua,Zhang, Dawei,et al. Self-supervised graph representation learning via bootstrapping[J]. NEUROCOMPUTING,2021,456:88-96.
APA Che, Feihu,Yang, Guohua,Zhang, Dawei,Tao, Jianhua,&Liu, Tong.(2021).Self-supervised graph representation learning via bootstrapping.NEUROCOMPUTING,456,88-96.
MLA Che, Feihu,et al."Self-supervised graph representation learning via bootstrapping".NEUROCOMPUTING 456(2021):88-96.
Files in This Item: Download All
File Name/Size DocType Version Access License
Self-supervised grap(1379KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Che, Feihu]'s Articles
[Yang, Guohua]'s Articles
[Zhang, Dawei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Che, Feihu]'s Articles
[Yang, Guohua]'s Articles
[Zhang, Dawei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Che, Feihu]'s Articles
[Yang, Guohua]'s Articles
[Zhang, Dawei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Self-supervised graph representation learning via bootstrapping.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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