模式识别与人工智能
Tuesday, Jul. 29, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2023, Vol. 36 Issue (4): 287-299    DOI: 10.16451/j.cnki.issn1003-6059.202304001
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Self-Supervised Heterogeneous Graph Neural Network Model Based on Collaborative Contrastive Learning of Topology Information and Attribute Information
LI Chao1, SUN Guoyi1, YAN Yeyu1, DUAN Hua3, ZENG Qingtian2
1. College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590;
2. College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao 266590;
3. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590

Download: PDF (917 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The complex structure and rich semantics of heterogeneous graphs can be fully explored by heterogeneous graph neural network models. However, there is mutual interference between attribute information and topology information in the model construction process, resulting in weakened expression capability. Therefore, a self-supervised heterogeneous graph neural network model based on collaborative contrastive learning of topology information and attribute information is proposed. Firstly, the representation of the target nodes is learned from both topological and attribute perspectives. Then, the collaborative contrastive algorithm is employed to optimize the node representation from both perspectives, reducing the interference between topology information and attribute information. Additionally, a positive sample generation method combining the number of meta-paths and node topology similarity is proposed in the self-supervised training process of the model. The experiments on real datasets demonstrate the superior performance of the proposed model. The model code can be found at https://github.com/sun281210/HGTA.
Key wordsGraph Neural Network      Heterogeneous Graph      Contrastive Learning      Self-Supervised Learning     
Received: 09 January 2023     
ZTFLH: TP 391  
Fund:National Key R&D Program of China(No.2022ZD0119500), Natural Science Foundation of Shandong Province(No.ZR2022MF268)
Corresponding Authors: ZENG Qingtian, Ph.D., professor. His research interests include big data analysis and mining, process mining and internet of things.   
About author:: LI Chao, Ph.D., associate professor. His research interests include network representation learning, social network analysis and re-commendation algorithm.SUN Guoyi, master student. His research interests include machine learning and heterogeneous graph neural network.YAN Yeyu, master student. His research interests include graph representation learning and heterogeneous graph neural network.DUAN Hua, Ph.D., professor. Her research interests include social network analysis, data mining and privacy preserving.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LI Chao
SUN Guoyi
YAN Yeyu
DUAN Hua
ZENG Qingtian
Cite this article:   
LI Chao,SUN Guoyi,YAN Yeyu等. Self-Supervised Heterogeneous Graph Neural Network Model Based on Collaborative Contrastive Learning of Topology Information and Attribute Information[J]. Pattern Recognition and Artificial Intelligence, 2023, 36(4): 287-299.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202304001      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2023/V36/I4/287
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