Label Incorporated Graph Neural Networks for Text Classification

被引:6
|
作者
Xin, Yuan [1 ]
Xu, Linli [1 ,3 ]
Guo, Junliang [1 ]
Li, Jiquan [1 ]
Sheng, Xin [1 ]
Zhou, Yuanyuan [2 ]
机构
[1] Univ Sci & Technol China, Sch Comp Sci & Technol, Anhui Prov Key Lab Big Data Anal & Applicat, Hefei, Peoples R China
[2] Univ Sci & Technol China, Informat Sci Ctr, Hefei, Peoples R China
[3] IFLYIEK Co Ltd, Hefei, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1109/ICPR48806.2021.9413086
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph Neural Networks (GNNs) have achieved great success on graph-structured data, and their applications on traditional data structures such as natural language processing and semi-supervised text classification have been extensively explored in recent years. While previous works only consider the text information while building the graph, heterogeneous information such as labels is ignored. In this paper, we consider incorporating the label information while building the graph by adding text-label-text paths, through which the supervision information will propagate among the graph more directly. Specifically, we treat labels as nodes in the graph which also contains text and word nodes, and then connect labels with texts belonging to that label. Through graph convolutions, label embeddings are jointly learned with text embeddings in the same latent semantic space. The newly incorporated label nodes will facilitate learning more accurate text embeddings by introducing the label information, and thus benefit the downstream text classification tasks. Extensive results on several benchmark datasets show that the proposed framework outperforms baseline methods by a significant margin.
引用
收藏
页码:8892 / 8898
页数:7
相关论文
共 50 条
  • [31] Parameterized Hypercomplex Graph Neural Networks for Graph Classification
    Le, Tuan
    Bertolini, Marco
    Noe, Frank
    Clevert, Djork-Arne
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT III, 2021, 12893 : 204 - 216
  • [32] A Neural Architecture for Multi-label Text Classification
    Coope, Sam
    Bachrach, Yoram
    Zukov-Gregoric, Andrej
    Rodriguez, Jose
    Maksak, Bogdan
    McMurtie, Conan
    Bordbar, Mahyar
    INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1, 2019, 868 : 676 - 691
  • [33] Label Contrastive Coding Based Graph Neural Network for Graph Classification
    Ren, Yuxiang
    Bai, Jiyang
    Zhang, Jiawei
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2021), PT I, 2021, 12681 : 123 - 140
  • [34] Text Classification with Attention Gated Graph Neural Network
    Zhaoyang Deng
    Chenxiang Sun
    Guoqiang Zhong
    Yuxu Mao
    Cognitive Computation, 2022, 14 : 1464 - 1473
  • [35] Text Classification with Attention Gated Graph Neural Network
    Deng, Zhaoyang
    Sun, Chenxiang
    Zhong, Guoqiang
    Mao, Yuxu
    COGNITIVE COMPUTATION, 2022, 14 (04) : 1464 - 1473
  • [36] Heterogeneous Graph Neural Network for Short Text Classification
    Zhang, Bingjie
    He, Qing
    Zhang, Damin
    APPLIED SCIENCES-BASEL, 2022, 12 (17):
  • [37] A Sequential Graph Neural Network for Short Text Classification
    Zhao, Ke
    Huang, Lan
    Song, Rui
    Shen, Qiang
    Xu, Hao
    ALGORITHMS, 2021, 14 (12)
  • [38] Label Correlation Based Graph Convolutional Network for Multi-label Text Classification
    Huy-The Vu
    Minh-Tien Nguyen
    Van-Chien Nguyen
    Manh-Tran Tien
    Van-Hau Nguyen
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [39] Label-representative graph convolutional network for multi-label text classification
    Huy-The Vu
    Minh-Tien Nguyen
    Van-Chien Nguyen
    Minh-Hieu Pham
    Van-Quyet Nguyen
    Van-Hau Nguyen
    Applied Intelligence, 2023, 53 : 14759 - 14774
  • [40] Label-representative graph convolutional network for multi-label text classification
    Huy-The Vu
    Minh-Tien Nguyen
    Van-Chien Nguyen
    Minh-Hieu Pham
    Van-Quyet Nguyen
    Van-Hau Nguyen
    APPLIED INTELLIGENCE, 2023, 53 (12) : 14759 - 14774