模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (12): 1093-1102    DOI: 10.16451/j.cnki.issn1003-6059.202112003
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Meta-Path and Hierarchical Attention Based Temporal Heterogeneous Information Network Representation Learning
QIN Haiying1, ZHAO Zhongying1, LI Jianhui1, LI Chao1
1. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590

Download: PDF (1021 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Heterogeneous information network representation learning is widely applied in many fields including node classification, link prediction and personalized recommendation. The existing heterogeneous information network representation learning methods mainly focus on static networks but ignore the influence of time on node representations. To address this problem, a meta-path and hierarchical attention based temporal heterogeneous network representation learning method is proposed. The meta-paths are utilized to capture the structural and semantic information in heterogeneous information networks. Through the time decay attention layer, the impact of different meta-path instances at a specific time on the target node is captured. Through the meta-path level attention, the node representation under different meta-paths is fused to obtain the final representation. The experiments on DBLP and IMDB datasets show that the proposed method achieves better results on the tasks of node classification and node clustering.
Key wordsTemporal Heterogeneous Information Network      Representation Learning      Meta-Path      Time Decay Attention     
Received: 22 April 2021     
ZTFLH: TP 391  
Fund:National Natural Science Foundation of China(No.62072288,61702306), Natural Science Foundation of Shandong Province(No.ZR2018BF013)
Corresponding Authors: ZHAO Zhongying, Ph.D., associate professor. Her research interests include social network analysis and data mining.   
About author:: QIN Haiying, master student. Her research interests include heterogeneous information network representation learning and application.
LI Jianhui, master student. His research interests include network representation lear-ning and recommendation system.
LI Chao, Ph.D., associate professor. His research interests include big data analysis, social network analysis and data mining.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
QIN Haiying
ZHAO Zhongying
LI Jianhui
LI Chao
Cite this article:   
QIN Haiying,ZHAO Zhongying,LI Jianhui等. Meta-Path and Hierarchical Attention Based Temporal Heterogeneous Information Network Representation Learning[J]. , 2021, 34(12): 1093-1102.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202112003      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I12/1093
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn