Semi-Supervised Graph Attention Networks for Event Representation Learning

被引:4
|
作者
Rodrigues Mattos, Joao Pedro [1 ]
Marcacini, Ricardo M. [1 ]
机构
[1] Univ Sao Paulo, Inst Math & Comp Sci ICMC, Sao Carlos, Brazil
基金
巴西圣保罗研究基金会;
关键词
network embeddings; event analysis; representation learning;
D O I
10.1109/ICDM51629.2021.00150
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Event analysis from news and social networks is very useful for a wide range of social studies and real-world applications. Recently, event graphs have been explored to model event datasets and their complex relationships, where events are vertices connected to other vertices representing locations, people's names, dates, and various other event metadata. Graph representation learning methods are promising for extracting latent features from event graphs to enable the use of different classification algorithms. However, existing methods fail to meet essential requirements for event graphs, such as (i) dealing with semi-supervised graph embedding to take advantage of some labeled events, (ii) automatically determining the importance of the relationships between event vertices and their metadata vertices, as well as (iii) dealing with the graph heterogeneity. This paper presents GNEE (GAT Neural Event Embeddings), a method that combines Graph Attention Networks and Graph Regularization. First, an event graph regularization is proposed to ensure that all graph vertices receive event features, thereby mitigating the graph heterogeneity drawback. Second, semi-supervised graph embedding with self-attention mechanism considers existing labeled events, as well as learns the importance of relationships in the event graph during the representation learning process. A statistical analysis of experimental results with five real-world event graphs and six graph embedding methods shows that our GNEE outperforms state-of-the-art semi-supervised graph embedding methods.
引用
收藏
页码:1234 / 1239
页数:6
相关论文
共 50 条
  • [1] NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning
    Hu, Jianke
    Zhang, Yin
    [J]. FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2022, 23 (03) : 409 - 421
  • [2] Word and graph attention networks for semi-supervised classification
    Jing Zhang
    Mengxi Li
    Kaisheng Gao
    Shunmei Meng
    Cangqi Zhou
    [J]. Knowledge and Information Systems, 2021, 63 : 2841 - 2859
  • [3] Word and graph attention networks for semi-supervised classification
    Zhang, Jing
    Li, Mengxi
    Gao, Kaisheng
    Meng, Shunmei
    Zhou, Cangqi
    [J]. KNOWLEDGE AND INFORMATION SYSTEMS, 2021, 63 (11) : 2841 - 2859
  • [4] Hierarchical graph attention networks for semi-supervised node classification
    Kangjie Li
    Yixiong Feng
    Yicong Gao
    Jian Qiu
    [J]. Applied Intelligence, 2020, 50 : 3441 - 3451
  • [5] Semi-supervised User Profiling with Heterogeneous Graph Attention Networks
    Chen, Weijian
    Gu, Yulong
    Ren, Zhaochun
    He, Xiangnan
    Xie, Hongtao
    Guo, Tong
    Yin, Dawei
    Zhang, Yongdong
    [J]. PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 2116 - 2122
  • [6] Hierarchical graph attention networks for semi-supervised node classification
    Feng, Yixiong
    Li, Kangjie
    Gao, Yicong
    Qiu, Jian
    [J]. APPLIED INTELLIGENCE, 2020, 50 (10) : 3441 - 3451
  • [7] Graph Ensemble Networks for Semi-supervised Embedding Learning
    Tang, Hui
    Liang, Xun
    Wu, Bo
    Guan, Zhenyu
    Guo, Yuhui
    Zheng, Xiangping
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, 2021, 12815 : 408 - 420
  • [8] Graph Stochastic Neural Networks for Semi-supervised Learning
    Wang, Haibo
    Zhou, Chuan
    Chen, Xin
    Wu, Jia
    Pan, Shirui
    Wang, Jilong
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [9] Semi-supervised Learning with Graph Learning-Convolutional Networks
    Jiang, Bo
    Zhang, Ziyan
    Lin, Doudou
    Tang, Jin
    Luo, Bin
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 11305 - 11312
  • [10] Flexible data representation with graph convolution for semi-supervised learning
    Dornaika, Fadi
    [J]. NEURAL COMPUTING & APPLICATIONS, 2021, 33 (12): : 6851 - 6863