Self-supervised graph representation learning via bootstrapping

doi:10.1016/j.neucom.2021.03.123

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 智能交互

	Self-supervised graph representation learning via bootstrapping
	Che, Feihu 1,2; Yang, Guohua 1; Zhang, Dawei 1; Tao, Jianhua 1,2,3; Liu, Tong 1
刊名	NEUROCOMPUTING
	2021-10-07
卷号	456 页码:88-96
关键词	Graph representation learning Self-supervised Bootstrapping Graph neural network
ISSN号	0925-2312
DOI	10.1016/j.neucom.2021.03.123
通讯作者	Tao, Jianhua(jhtao@nlpr.ia.ac.cn)
英文摘要	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.
资助项目	National 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]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000687471900008
资助机构	National Key Research and Develop ment Plan of China ; National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45911]
专题	模式识别国家重点实验室_智能交互
通讯作者	Tao, Jianhua
作者单位	1.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
推荐引用方式 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.