HeMGNN: Heterogeneous Network Embedding Based on a Mixed Graph Neural Network

被引:2
作者
Zhong, Hongwei [1 ]
Wang, Mingyang [1 ]
Zhang, Xinyue [1 ]
机构
[1] Northeast Forestry Univ, Coll Informat & Comp Engn, Harbin 150040, Peoples R China
基金
中国国家自然科学基金;
关键词
heterogeneous network; network embedding; metapath; graph neural network;
D O I
10.3390/electronics12092124
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Network embedding is an effective way to realize the quantitative analysis of large-scale networks. However, mainstream network embedding models are limited by the manually pre-set metapaths, which leads to the unstable performance of the model. At the same time, the information from homogeneous neighbors is mostly focused in encoding the target node, while ignoring the role of heterogeneous neighbors in the node embedding. This paper proposes a new embedding model, HeMGNN, for heterogeneous networks. The framework of the HeMGNN model is divided into two modules: the metapath subgraph extraction module and the node embedding mixing module. In the metapath subgraph extraction module, HeMGNN automatically generates and filters out the metapaths related to domain mining tasks, so as to effectively avoid the excessive dependence of network embedding on artificial prior knowledge. In the node embedding mixing module, HeMGNN integrates the information of homogeneous and heterogeneous neighbors when learning the embedding of the target nodes. This makes the node vectors generated according to the HeMGNN model contain more abundant topological and semantic information provided by the heterogeneous networks. The Rich semantic information makes the node vectors achieve good performance in downstream domain mining tasks. The experimental results show that, compared to the baseline models, the average classification and clustering performance of HeMGNN has improved by up to 0.3141 and 0.2235, respectively.
引用
收藏
页数:15
相关论文
共 31 条
[1]   MEGNN: Meta-path extracted graph neural network for heterogeneous [J].
Chang, Yaomin ;
Chen, Chuan ;
Hu, Weibo ;
Zheng, Zibin ;
Zhou, Xiaocong ;
Chen, Shouzhi .
KNOWLEDGE-BASED SYSTEMS, 2022, 235
[2]   metapath2vec: Scalable Representation Learning for Heterogeneous Networks [J].
Dong, Yuxiao ;
Chawla, Nitesh V. ;
Swami, Ananthram .
KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2017, :135-144
[3]   Graph Embedding Framework Based on Adversarial and Random Walk Regularization [J].
Dou, Wei ;
Zhang, Weiyu ;
Weng, Ziqiang ;
Xia, Zhongxiu .
IEEE ACCESS, 2021, 9 :1454-1464
[4]   HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning [J].
Fu, Tao-yang ;
Lee, Wang-Chien ;
Lei, Zhen .
CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, :1797-1806
[5]   Adversarial Learning on Heterogeneous Information Networks [J].
Hu, Binbin ;
Fang, Yuan ;
Shi, Chuan .
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :120-129
[6]   MBRep: Motif-based representation learning in heterogeneous networks [J].
Hu, Qian ;
Lin, Fan ;
Wang, Beizhan ;
Li, Chunyan .
EXPERT SYSTEMS WITH APPLICATIONS, 2022, 190
[7]   Heterogeneous Graph Transformer [J].
Hu, Ziniu ;
Dong, Yuxiao ;
Wang, Kuansan ;
Sun, Yizhou .
WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020), 2020, :2704-2710
[8]   ABLE: Meta-Path Prediction in Heterogeneous Information Networks [J].
Huang, Chenji ;
Fang, Yixiang ;
Lin, Xuemin ;
Cao, Xin ;
Zhang, Wenjie .
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2022, 16 (04)
[9]   A distributed model for sampling large scale social networks [J].
Jaouadi, Myriam ;
Ben Romdhane, Lotfi .
EXPERT SYSTEMS WITH APPLICATIONS, 2021, 186
[10]   Learning ladder neural networks for semi-supervised node classification in social network [J].
Li, Bentian ;
Pi, Dechang ;
Lin, Yunxia .
EXPERT SYSTEMS WITH APPLICATIONS, 2021, 165