InducT-GCN: Inductive Graph Convolutional Networks for Text Classification

被引:20
|
作者
Wang, Kunze [1 ]
Han, Soyeon Caren [1 ]
Poon, Josiah [1 ]
机构
[1] Univ Sydney, Sch Comp Sci, Sydney, NSW, Australia
关键词
D O I
10.1109/ICPR56361.2022.9956075
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Text classification aims to assign labels to textual units by making use of global information. Recent studies have applied graph neural network (GNN) to capture the global word co-occurrence in a corpus. Existing approaches require that all the nodes (training and test) in a graph are present during training, which are transductive and do not naturally generalise to unseen nodes. To make those models inductive, they use extra resources, like pretrained word embedding. However, high-quality resource is not always available and hard to train. Under the extreme settings with no extra resource and limited amount of training set, can we still learn an inductive graph-based text classification model? In this paper, we introduce a novel inductive graph-based text classification framework, InducT-GCN (InducTive Graph Convolutional Networks for Text classification). Compared to transductive models that require test documents in training, we construct a graph based on the statistics of training documents only and represent document vectors with a weighted sum of word vectors. We then conduct one-directional GCN propagation during testing. Across five text classification benchmarks, our InducT-GCN outperformed state-of-the-art methods that are either transductive in nature or pre-trained additional resources. We also conducted scalability testing by gradually increasing the data size and revealed that our InducT-GCN can reduce the time and space complexity. The code is available on: https://github.com/usydnlp/InductTGCN.
引用
收藏
页码:1243 / 1249
页数:7
相关论文
共 50 条
  • [1] Graph Convolutional Networks for Text Classification
    Yao, Liang
    Mao, Chengsheng
    Luo, Yuan
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 7370 - 7377
  • [2] Tensor Graph Convolutional Networks for Text Classification
    Liu, Xien
    You, Xinxin
    Zhang, Xiao
    Wu, Ji
    Lv, Ping
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 8409 - 8416
  • [3] Graph Convolutional Networks for Fast Text Classification
    Cai, Houyv
    Lv, Shaoqing
    Lu, Guangyue
    Li, Tingting
    Proceedings - 2022 4th International Conference on Natural Language Processing, ICNLP 2022, 2022, : 420 - 425
  • [4] Local discriminative graph convolutional networks for text classification
    Wang, Bolin
    Sun, Yuanyuan
    Chu, Yonghe
    Min, Changrong
    Yang, Zhihao
    Lin, Hongfei
    MULTIMEDIA SYSTEMS, 2023, 29 (04) : 2363 - 2373
  • [5] Local discriminative graph convolutional networks for text classification
    Bolin Wang
    Yuanyuan Sun
    Yonghe Chu
    Changrong Min
    Zhihao Yang
    Hongfei Lin
    Multimedia Systems, 2023, 29 : 2363 - 2373
  • [6] HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification
    Ragesh, Rahul
    Sellamanickam, Sundararajan
    Iyer, Arun
    Bairi, Ramakrishna
    Lingam, Vijay
    WSDM '21: PROCEEDINGS OF THE 14TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2021, : 860 - 868
  • [7] AS-GCN: Adaptive Semantic Architecture of Graph Convolutional Networks for Text-Rich Networks
    Yu, Zhizhi
    Jin, Di
    Liu, Ziyang
    He, Dongxiao
    Wang, Xiao
    Tong, Hanghang
    Han, Jiawei
    2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021), 2021, : 837 - 846
  • [8] Tibetan News Text Classification Based on Graph Convolutional Networks
    Xu G.
    Zhang Z.
    Yu S.
    Dong Y.
    Tian Y.
    Data Analysis and Knowledge Discovery, 2023, 7 (06) : 73 - 85
  • [9] Privacy-Preserving Graph Convolutional Networks for Text Classification
    Igamberdiev, Timour
    Habernal, Ivan
    LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 338 - 350
  • [10] Contrastive Graph Convolutional Networks with adaptive augmentation for text classification
    Yang, Yintao
    Miao, Rui
    Wang, Yili
    Wang, Xin
    INFORMATION PROCESSING & MANAGEMENT, 2022, 59 (04)