Learning Embeddings Based on Global Structural Similarity in Heterogeneous Networks

Wanting Wen; Daniel D. Zeng; Jie Bai; Kang Zhao; Ziqiang Li

doi:10.1109/MIS.2020.3027677

Back

Learning Embeddings Based on Global Structural Similarity in Heterogeneous Networks

Journal article

Peer reviewed

Learning Embeddings Based on Global Structural Similarity in Heterogeneous Networks

Wanting Wen, Daniel D. Zeng, Jie Bai, Kang Zhao and Ziqiang Li

IEEE intelligent systems, Vol.36(6), pp.13-22

11/01/2021

DOI: 10.1109/MIS.2020.3027677

View Online

Abstract

With different types of nodes and edges, heterogeneous networks have higher levels of structural diversity than homogeneous networks. This article proposes an unsupervised representation learning model, named gs2vec, to address structural diversity of a node being connected to other types of nodes via different types of edges in heterogeneous networks. The model measures a node's structural roles based on its numbers of neighboring nodes of different types. It also attempts to measure such structural roles beyond the immediate neighborhood of each node by incorporating structural roles of other nodes k-hop away. Experiments based on synthetic and empirical datasets show that gs2vec outperforms state-of-the-art network representation learning models in heterogeneous network analysis tasks such as node classification and node clustering.

Computer Science

Computer Science, Artificial Intelligence

Engineering

Engineering, Electrical & Electronic

Science & Technology

Technology

Details

Title: Subtitle: Learning Embeddings Based on Global Structural Similarity in Heterogeneous Networks
Creators: Wanting Wen - [TheStateKeyLaboratoryofManagementandControlforComplexSystems, InstituteofAutomation,ChineseAcademyofSciences, Beijing, Beijing China (e-mail: wanting.wen@ia.ac.cn)]
Daniel D. Zeng - [TheStateKeyLaboratoryofManagementandControlforComplexSystems, InstituteofAutomation,ChineseAcademyofSciences, BeiJing, Beijing China (e-mail: dajun.zeng@ia.ac.cn)]
Jie Bai - [TheStateKeyLaboratoryofManagementandControlforComplexSystems, InstituteofAutomation,ChineseAcademyofSciences, Beijing, Beijing China (e-mail: baijie2013@ia.ac.cn)]
Kang Zhao - University of Iowa
Ziqiang Li - [TheStateKeyLaboratoryofManagementandControlforComplexSystems, InstituteofAutomation,ChineseAcademyofSciences, Beijing, Beijing China (e-mail: ziqiang.li@ia.ac.cn)]
Resource Type: Journal article
Publication Details: IEEE intelligent systems, Vol.36(6), pp.13-22
Publisher: IEEE
DOI: 10.1109/MIS.2020.3027677
ISSN: 1541-1672
eISSN: 1941-1294
Number of pages: 10
Grant note: 71621002; 71902179 / NSFC; National Natural Science Foundation of China (NSFC) ZDRW-XH-2017-3 / CAS Key Grant 2016QY02D0305 / Ministry of Science and Technology of China Major Grant
Language: English
Date published: 11/01/2021
Academic Unit: Business Analytics
Record Identifier: 9984380383202771

Metrics

13 Record Views

2 Times Cited - Web of Science