RAHG: A Role-Aware Hypergraph Neural Network for Node Classification in Graphs

被引:3
|
作者
Li, Kunhao [1 ]
Huang, Zhenhua [1 ]
Jia, Zhaohong [1 ]
机构
[1] Anhui Univ, Sch Internet, Hefei 230061, Peoples R China
基金
中国国家自然科学基金;
关键词
Graph neural networks; graph representation; node classification; hypergraph;
D O I
10.1109/TNSE.2023.3243058
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Graph neural networks have been widely studied and applied to node classification in graph-format datasets in recent years. Traditional graph neural networks mainly consider the adjacency characteristics of nodes and fail to learn rich role representations of nodes. Existing role representations methods of nodes are mostly in unsupervised approaches, resulting in unsatisfactory performance in downstream tasks. A graph can be reorganized as a hypergraph, in which the role characteristics of nodes are more intuitively represented. Based on this, we propose a role-aware hypergraph neural network (RAHG) that utilizes hypergraphs and an attention mechanism to fuse nodes' role and adjacency representations. A residual network is also applied to relieve the smoothing problem between layers in the model. The model adjusts the weights on the role and adjacency representations according to the characteristics of the graphs. RAHG significantly improves the prediction performance compared with existing graph neural networks on seven datasets, with accuracy increased by up to 12.1% on the node classification task in graphs.
引用
收藏
页码:2098 / 2108
页数:11
相关论文
共 50 条
  • [1] A General Heterogeneous Hypergraph Neural Network for Node Classification
    Hu, Bingde
    Huang, Wenjie
    Zheng, Tongya
    Song, Mingli
    Li, Ying
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [2] Role-aware random walk for network embedding
    Zhang, Hegui
    Kou, Gang
    Peng, Yi
    Zhang, Boyu
    [J]. INFORMATION SCIENCES, 2024, 652
  • [3] Hierarchical Structure-Feature Aware Graph Neural Network for Node Classification
    Yao, Wenbin
    Guo, Ke
    Hou, Yingying
    Li, Xiaoyong
    [J]. IEEE ACCESS, 2022, 10 : 36846 - 36855
  • [4] Knowledge-Aware Hypergraph Neural Network for Recommender Systems
    Liu, Binghao
    Zhao, Pengpeng
    Zhuang, Fuzhen
    Xian, Xuefeng
    Liu, Yanchi
    Sheng, Victor S.
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2021), PT III, 2021, 12683 : 132 - 147
  • [5] Gated Hypergraph Neural Network for Scene-Aware Recommendation
    Yang, Tianchi
    Zhang, Luhao
    Shi, Chuan
    Yang, Cheng
    Xu, Siyong
    Fang, Ruiyu
    Hu, Maodi
    Liu, Huaijun
    Li, Tao
    Wang, Dong
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT II, 2022, : 199 - 215
  • [6] Neural Feature-aware Recommendation with Signed Hypergraph Convolutional Network
    Chen, Xu
    Xiong, Kun
    Zhang, Yongfeng
    Xia, Long
    Yin, Dawei
    Huang, Jimmy Xiangji
    [J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2020, 39 (01)
  • [7] Research on migraine classification model based on hypergraph neural network
    Shen, Guangfeng
    Zeng, Weiming
    Yang, Jiajun
    [J]. JOURNAL OF SUPERCOMPUTING, 2024, 80 (17): : 25403 - 25423
  • [8] Hyperspectral Image Classification Based on Hypergraph and Convolutional Neural Network
    Liu Yuzhen
    Jiang Zhengquan
    Mai Fei
    Zhang Chunhua
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2019, 56 (11)
  • [9] EHGNN: Enhanced Hypergraph Neural Network for Hyperspectral Image Classification
    Wang, Qingwang
    Huang, Jiangbo
    Shen, Tao
    Gu, Yanfeng
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21 : 1 - 5
  • [10] State-element-aware syndrome classification based on hypergraph convolutional network
    Teng, Shenghua
    Ma, Jishun
    Li, Zuoyong
    Zhou, Chang'en
    Lu, Weikai
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 248