CASIA OpenIR  > 模式识别国家重点实验室  > 智能交互
Multi-aspect self-supervised learning for heterogeneous information network
Che, Feihu1,2; Tao, Jianhua1,2,3; Yang, Guohua1; Liu, Tong1; Zhang, Dawei1
Source PublicationKNOWLEDGE-BASED SYSTEMS
ISSN0950-7051
2021-12-05
Volume233Pages:14
Abstract

Graph neural networks (GNNs) have made remarkable advancements in processing graph-structured data with all nodes and edges belonging to the same type. However, various types of node and relations exist in heterogeneous information networks (HINs), and due to this, HINs contain rich structural and semantic information. To tackle this heterogeneity, existing methods usually apply several well-designed metapaths to HINs to obtain the corresponding homogeneous subgraphs. However, these methods either fail to capture the interconnections between the same nodes in different subgraphs or require qualified labels. To address these issues, we propose a new multi-aspect self-supervised learning (SSL) framework for HIN representation in an unsupervised manner: (1) we design a new contrastive learning model to capture the similarities between the same nodes in different homogeneous subgraphs, and (2) we maximize the mutual information between the local patches and the global representation in one subgraph. Extensive experiments on various downstream tasks demonstrate the superiority of our model in comparison to the existing state-of-the-art methods. (c) 2021 Elsevier B.V. All rights reserved.

KeywordHeterogeneous information network Self-supervised Contrastive learning Graph neural network
DOI10.1016/j.knosys.2021.107474
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000709919000012
PublisherELSEVIER
Sub direction classification知识表示与推理
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/46304
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,Tao, Jianhua,Yang, Guohua,et al. Multi-aspect self-supervised learning for heterogeneous information network[J]. KNOWLEDGE-BASED SYSTEMS,2021,233:14.
APA Che, Feihu,Tao, Jianhua,Yang, Guohua,Liu, Tong,&Zhang, Dawei.(2021).Multi-aspect self-supervised learning for heterogeneous information network.KNOWLEDGE-BASED SYSTEMS,233,14.
MLA Che, Feihu,et al."Multi-aspect self-supervised learning for heterogeneous information network".KNOWLEDGE-BASED SYSTEMS 233(2021):14.
Files in This Item:
File Name/Size DocType Version Access License
Multi-aspect self-su(2661KB)期刊论文作者接受稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Che, Feihu]'s Articles
[Tao, Jianhua]'s Articles
[Yang, Guohua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Che, Feihu]'s Articles
[Tao, Jianhua]'s Articles
[Yang, Guohua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Che, Feihu]'s Articles
[Tao, Jianhua]'s Articles
[Yang, Guohua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-aspect self-supervised learning for heterogeneous information.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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