Self-supervised graph representation learning via bootstrapping
Che, Feihu1,2; Yang, Guohua1; Zhang, Dawei1; Tao, Jianhua1,2,3; Liu, Tong1
发表期刊NEUROCOMPUTING
ISSN0925-2312
2021-10-07
卷号456页码:88-96
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.

关键词Graph representation learning Self-supervised Bootstrapping Graph neural network
DOI10.1016/j.neucom.2021.03.123
收录类别SCI
语种英语
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]
项目资助者National Key Research and Develop ment Plan of China ; National Natural Science Foundation of China (NSFC)
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000687471900008
出版者ELSEVIER
七大方向——子方向分类知识表示与推理
引用统计
被引频次:11[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/45912
专题多模态人工智能系统全国重点实验室_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
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Self-supervised grap(1379KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Che, Feihu]的文章
[Yang, Guohua]的文章
[Zhang, Dawei]的文章
百度学术
百度学术中相似的文章
[Che, Feihu]的文章
[Yang, Guohua]的文章
[Zhang, Dawei]的文章
必应学术
必应学术中相似的文章
[Che, Feihu]的文章
[Yang, Guohua]的文章
[Zhang, Dawei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Self-supervised graph representation learning via bootstrapping.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。