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 50 条
  • [41] Sequence Contained Heterogeneous Graph Neural Network
    Zhang, Shanshan
    Huang, Tiancheng
    Wang, Donglin
    [J]. 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [42] Heterogeneous graph neural network for attribute completion
    Wang, Kai
    Yu, Yanwei
    Huang, Chao
    Zhao, Zhongying
    Dong, Junyu
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 251
  • [43] Trajectory Prediction with Heterogeneous Graph Neural Network
    Li, Guanlue
    Luo, Guiyang
    Yuan, Quan
    Li, Jinglin
    [J]. PRICAI 2022: TRENDS IN ARTIFICIAL INTELLIGENCE, PT II, 2022, 13630 : 375 - 387
  • [44] Accelerating Virtual Network Embedding with Graph Neural Networks
    Habibi, Farzad
    Dolati, Mahdi
    Khonsari, Ahmad
    Ghaderi, Majid
    [J]. 2020 16TH INTERNATIONAL CONFERENCE ON NETWORK AND SERVICE MANAGEMENT (CNSM), 2020,
  • [45] Collaborative Graph Neural Networks for Attributed Network Embedding
    Tan, Qiaoyu
    Zhang, Xin
    Huang, Xiao
    Chen, Hao
    Li, Jundong
    Hu, Xia
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (03) : 972 - 986
  • [46] Multisource hierarchical neural network for knowledge graph embedding
    Jiang, Dan
    Wang, Ronggui
    Xue, Lixia
    Yang, Juan
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 237
  • [47] Heterogeneous Graph Network Embedding for Sentiment Analysis on Social Media
    Zhigang Jin
    Xiaofang Zhao
    Yuhong Liu
    [J]. Cognitive Computation, 2021, 13 : 81 - 95
  • [48] Heterogeneous Graph Network Embedding for Sentiment Analysis on Social Media
    Jin, Zhigang
    Zhao, Xiaofang
    Liu, Yuhong
    [J]. COGNITIVE COMPUTATION, 2021, 13 (01) : 81 - 95
  • [49] Heterogeneous Information Network Embedding with Convolutional Graph Attention Networks
    Cao, Meng
    Ma, Xiying
    Zhu, Kai
    Xu, Ming
    Wang, Chongjun
    [J]. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [50] An integrated simplicial neural network with neuro-fuzzy network for graph embedding
    Pham, Phu
    [J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024,