基于图神经网络的文本分类方法研究综述

doi:10.3778/j.issn.1002-8331.2403-0142

摘要/Abstract

摘要： 文本分类是自然语言处理领域中的一个重要任务，旨在将给定的文本数据分配到预定义的一组类别中。传统的文本分类方法只能处理欧氏空间的数据，不能处理图这种非欧氏数据。而对于图结构的文本数据无法直接处理，无法捕捉图中的非欧氏结构。因此，如何将图神经网络应用到文本分类任务中是目前的研究热点之一。对基于图神经网络的文本分类方法进行了综述，概述了基于机器学习和基于深度学习的传统文本分类方法，总结了图卷积神经网络的背景和原理；根据不同类型的图网络详细阐述了基于图神经网络的文本分类方法，同时对图神经网络模型在文本分类中的应用进行了深入分析；对目前基于图神经网络的文本分类模型进行了对比实验，讨论了模型的分类性能；提出了未来的研究方向，以推动该领域的进一步发展。

关键词: 文本分类, 自然语言处理, 图神经网络, 图网络

Abstract: Text classification is an important task in the field of natural language processing, aiming to assign given text data to a predefined set of categories. Traditional text classification methods can only handle data in Euclidean space and cannot process non-Euclidean data such as graphs. For text data with graph structure, it is not directly processable and cannot capture the non-Euclidean structure in the graph. Therefore, how to apply graph neural networks to text classification tasks is one of the current research hotspots. This paper reviews the text classification methods based on graph neural networks. Firstly, it outlines the traditional text classification methods based on machine learning and deep learning, and summarizes the background and principles of graph convolutional neural networks. Secondly, it elaborates on the text classification methods based on graph neural networks according to different types of graph networks, and conducts an in-depth analysis of the application of graph neural network models in text classification. Then, it compares the current text classification models based on graph neural networks through comparative experiments and discusses the classification performance of the models. Finally, it proposes future research directions to further promote the development of this field.

Key words: text classification, natural language processing, graph neural networks, graph networks

苏易礌, 李卫军, 刘雪洋, 丁建平, 刘世侠, 李浩南, 李贯峰. 基于图神经网络的文本分类方法研究综述[J]. 计算机工程与应用, 2024, 60(19): 1-17.

SU Yilei, LI Weijun, LIU Xueyang, DING Jianping, LIU Shixia, LI Haonan, LI Guanfeng. Review of Text Classification Methods Based on Graph Neural Networks[J]. Computer Engineering and Applications, 2024, 60(19): 1-17.

参考文献

[1] 陈秀明, 储天启, 王先传. 基于LSTM-CNN-Attention的新闻分类研究[J]. 阜阳师范大学学报(自然科学版), 2022, 39(4): 62-69.
CHEN X M, CHU T Q, WANG X C. Research on news classification based on LSTM-CNN-Attention[J]. Journal of Fuyang Normal University(Natural Science), 2022, 39(4):62-69.
[2] 李阳, 王石, 朱俊武, 等. 方面级情感分析综述[J]. 计算机科学, 2023, 50(S1): 34-40.
LI Y, WANG S, ZHU J W, et al. Summarization of aspect-level sentiment analysis [J]. Computer Science, 2023, 50(S1): 34-40.
[3] 任伟建, 刘圆圆, 计妍, 等. 基于RNN-LSTM新冠肺炎疫情下的微博舆情分析[J]. 吉林大学学报(信息科学版), 2022, 40(4): 581-588.
REN W J, LIU Y Y, JI Y, et al. Public opinion analysis on Weibo based on RNN-LSTM in COVID-19[J]. Journal of Jilin University (Information Science Edition), 2022, 40(4): 581-588.
[4] 余新言, 曾诚, 王乾, 等. 基于知识增强和提示学习的小样本新闻主题分类方法[J]. 计算机应用, 2024, 44(6): 1767-1774.
YU X Y, ZENG C, WANG Q, et al. Few-shot news topic classification method based on knowledge enhancement and prompt learning[J]. Journal of Computer Applications, 2024, 44(6): 1767-1774.
[5] ZAVRAK S, YILMAZ S. Email spam detection using hierarchical attention hybrid deep learning method[J]. Expert Systems with Applications, 2023, 233: 120977.
[6] 闫悦, 郭晓然, 王铁君, 等. 问答系统研究综述[J]. 计算机系统应用, 2023, 32(8): 1-18.
YAN Y, GUO X R, WANG T J, et al. Survey on question answering system research [J]. Computer Systems &?Applications, 2023, 32(8): 1-18.
[7] WAN C H, LEE L H, RAJKUMAR R, et al. A hybrid text classification approach with low dependency on parameter by integrating K-nearest neighbor and support vector machine[J]. Expert Systems with Applications, 2012, 39(15): 11880-11888.
[8] 辛梓铭, 王芳. 基于改进朴素贝叶斯算法的文本分类研究[J]. 燕山大学学报, 2023, 47(1): 82-88.
XIN Z M, WANG F. Research on text classification based on improved naive Bayes algorithm[J]. Journal of Yanshan University, 2023, 47(1): 82-88.
[9] XIONG L, YAO Y. Study on an adaptive thermal comfort model with K-nearest-neighbors (KNN) algorithm[J]. Building and Environment, 2021, 202: 108026.
[10] GUAN X, LIANG J, QIAN Y, et al. A multi-view OVA model based on decision tree for multi-classification tasks[J]. Knowledge-Based Systems, 2017, 138: 208-219.
[11] JALAL N, MEHMOOD A, CHOI G S, et al. A novel improved random forest for text classification using feature ranking and optimal number of trees[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34(6): 2733-2742.
[12] ZHAO R, MAO K. Fuzzy bag-of-words model for document representation[J]. IEEE Transactions on Fuzzy Systems, 2017, 26(2): 794-804.
[13] ALMAHMOUD R H, HAMMO B H. SEWAR: a corpus-based N-gram approach for extracting semantically-related words from Arabic medical corpus[J]. Expert Systems with Applications, 2024, 238: 121767.
[14] VAN ZAANEN M, KANTERS P H M. Automatic mood classification using TF* IDF based on lyrics[C]//Proceedings of the 11th International Society for Music Information Retrieval Conference (ISMIR 2010), 2010: 75-80.
[15] 裴志利, 阿茹娜, 姜明洋, 等. 基于卷积神经网络的文本分类研究综述[J]. 内蒙古民族大学学报(自然科学版), 2019, 34(3): 206-210.
PEI Z L, A R N, JIANG M Y, et al. Survey of text classification research based on convolutional neural networks[J]. Journal of Innner Mongolia University for Nationalities (Natural Science), 2019, 34(3): 206-210.
[16] 杨丽, 吴雨茜, 王俊丽, 等. 循环神经网络研究综述[J]. 计算机应用, 2018, 38(S2): 1-6.
YANG L, WU Y X, WANG J L, et al. Research on recurrent neural network[J]. Journal of Computer Applications, 2018, 38(S2): 1-6.
[17] 王鑫, 吴际, 刘超, 等. 基于LSTM循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报, 2018, 44(4): 772-784.
WANG X, WU J, LIU C, et al. Exploring LSTM based recurrent neural network for failure time series prediction[J].?Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(4): 772-784.
[18] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[19] ZHOU J, CUI G, HU S, et al. Graph neural networks: a review of methods and applications[J]. AI Open, 2020, 1: 57-81.
[20] 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述[J]. 计算机科学, 2022, 49(8): 205-216.
TAN Y Y, WANG J L, ZHANG C B. Review of text classification methods based on graph convolutional network[J]. Computer Science, 2022, 49(8): 205-216.
[21] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv:1710.10903, 2017.
[22] LI Y, TARLOW D, BROCKSCHMIDT M, et al. Gated graph sequence neural networks[J]. arXiv:1511.05493, 2015.
[23] YUN S, JEONG M, KIM R, et al. Graph transformer networks[C]//Advances in Neural Information Processing Systems, 2019, 32.
[24] GUAN B, ZHANG J, SETHARES W A, et al. SpecNet: spectral domain convolutional neural network[J]. arXiv:1905.10915, 2019.
[25] CHUNG F R K. Spectral graph theory[Z]. 1997.
[26] LE-TIEN T, TO T N, VO G. Graph-based signal processing to convolutional neural networks for medical image segmentation[J]. SEATUC Journal of Science and Engineering, 2022, 3(1): 9-15.
[27] VERMA D. Application of convolution theorem[J]. International Journal of Trend in Scientific Research and Development, 2018, 2(4): 981-984.
[28] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems, 2016, 29.
[29] LI R, WANG S, ZHU F, et al. Adaptive graph convolutional neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
[30] ZHUANG C, MA Q. Dual graph convolutional networks for graph-based semi-supervised classification[C]//Proceedings of the 2018 World Wide Web Conference, 2018: 499-508.
[31] XU B, SHEN H, CAO Q, et al. Graph wavelet neural network[J]. arXiv:1904.07785, 2019.
[32] MONTI F, BOSCAINI D, MASCI J, et al. Geometric deep learning on graphs and manifolds using mixture model CNNs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 5115-5124.
[33] GILMER J, SCHOENHOLZ S S, RILEY P F, et al. Neural message passing for quantum chemistry[C]//Proceedings of the International Conference on Machine Learning, 2017: 1263-1272.
[34] GAO H, WANG Z, JI S. Large-scale learnable graph convolutional networks[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 1416-1424.
[35] ZHANG M, CUI Z, NEUMANN M, et al. An end-to-end deep learning architecture for graph classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
[36] HAJIBABAEE P, MALEKZADEH M, HEIDARI M, et al. An empirical study of the graphsage and word2vec algorithms for graph multiclass classification[C]//Proceedings of the 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), 2021: 515-522.
[37] YING R, HE R, CHEN K, et al. Graph convolutional neural networks for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 974-983.
[38] HUANG W, ZHANG T, RONG Y, et al. Adaptive sampling towards fast graph representation learning[C]//Advances in Neural Information Processing Systems, 2018, 31.
[39] YAO L, MAO C, LUO Y. Graph convolutional networks for text classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 7370-7377.
[40] CHURCH K, HANKS P. Word association norms, mutual information, and lexicography[J]. Computational Linguistics, 1990, 16(1): 22-29.
[41] LIU X, YOU X, ZHANG X, et al. Tensor graph convolutional networks for text classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 8409-8416.
[42] WU F, SOUZA A, ZHANG T, et al. Simplifying graph convolutional networks[C]//Proceedings of the International Conference on Machine Learning, 2019: 6861-6871.
[43] WANG K, HAN S C, POON J. Induct-GCN: inductive graph convolutional networks for text classification[C]//Proceedings of the 2022 26th International Conference on Pattern Recognition (ICPR), 2022: 1243-1249.
[44] DAI Y, SHOU L, GONG M, et al. Graph fusion network for text classification[J]. Knowledge-Based Systems, 2022, 236: 107659.
[45] YANG L, CHEN H, LI Z, et al. Give us the facts: enhancing large language models with knowledge graphs for fact-aware language modeling[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3091-3110.
[46] SOYALP G, ALAR A, OZKANLI K, et al. Improving text classification with transformer[C]//Proceedings of the 2021 6th International Conference on Computer Science and Engineering (UBMK), 2021: 707-712.
[47] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[J]. arXiv:1810.04805, 2018.
[48] LIN Y, MENG Y, SUN X, et al. BertGCN: transductive text classification by combining GCN and BERT[J]. arXiv:2105.05727, 2021.
[49] XUE Y. BERTGACN: text classification by combining BERT and GCN and GAT[C]//Proceedings of the 2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE), 2023: 422-426.
[50] DONG K, LIU Y, XU F, et al. DCAT: combining multi- semantic dual-channel attention fusion for text classification[J]. IEEE Intelligent Systems, 2023, 38(4): 10-19.
[51] XU X, XU Z, LING Z, et al. Comprehensive implementation of TextCNN for enhanced collaboration between natural language processing and system recommendation[J]. arXiv:2403.09718, 2024.
[52] 李全鑫, 庞俊, 朱峰冉. 结合Bert与超图卷积网络的文本分类模型[J]. 计算机工程与应用, 2023, 59(17): 107-115.
LI Q X, PANG J, ZHU F R. Text classification method based on integration of Bert and hypergraph convolutional network[J]. Computer Engineering and Applications, 2023, 59(17): 107-115.
[53] LINMEI H, YANG T, SHI C, et al. Heterogeneous graph attention networks for semi-supervised short text classification[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019: 4821-4830.
[54] CHEN C, CHENG Z, LI Z, et al. Hypergraph attention networks[C]//Proceedings of the 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), 2020: 1560-1565.
[55] LI K, FENG Y, GAO Y, et al. Hierarchical graph attention networks for semi-supervised node classification[J]. Applied Intelligence, 2020, 50: 3441-3451.
[56] WANG X, WANG C, YANG H, et al. KGAT: an enhanced graph-based model for text classification[C]//Proceedings of the CCF International Conference on Natural Language Processing and Chinese Computing. Cham: Springer International Publishing, 2022: 656-668.
[57] 宋建平, 王毅, 孙开伟, 等. 结合双曲图注意力网络与标签信息的短文本分类方法[J]. 计算机工程与应用, 2024, 60(9): 188-195.
SONG J P, WANG Y, SUN K W, et al. Short text classification combined with hyperbolic graph attention networks and labels[J]. Computer Engineering and Applications, 2024, 60(9): 188-195.
[58] PATRICK M K, ADEKOYA A F, MIGHTY A A, et al. Capsule networks-a survey[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34(1): 1295-1310.
[59] BANG J, PARK J, PARK J. GACaps-HTC: graph attention capsule network for hierarchical text classification[J]. Applied Intelligence, 2023, 53(17): 20577-20594.
[60] ZHANG Y, YU X, CUI Z, et al. Every document owns its structure: inductive text classification via graph neural networks[J]. arXiv:2004.13826, 2020.
[61] DEY R, SALEM F M. Gate-variants of gated recurrent unit (GRU) neural networks[C]//Proceedings of the 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), 2017: 1597-1600.
[62] WANG Y, WANG C, ZHAN J, et al. Text FCG: fusing contextual information via graph learning for text classification[J]. Expert Systems with Applications, 2023, 219: 119658.
[63] ZHANG J, LIU F, XU W, et al. Feature fusion text classification model combining CNN and BiGRU with multi-attention mechanism[J]. Future Internet, 2019, 11(11): 237.
[64] LI W, LI S, MA S, et al. Recursive graphical neural networks for text classification[J]. arXiv:1909.08166, 2019.
[65] DENG Z, SUN C, ZHONG G, et al. Text classification with attention gated graph neural network[J]. Cognitive Computation, 2022, 14(4): 1464-1473.
[66] ZHENG S, ZHOU J, MENG K, et al. Label-dividing gated graph neural network for hierarchical text classification[C]//Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), 2022.
[67] ZHANG H, ZHANG J. Text graph transformer for document classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020.
[68] HU Z, DONG Y, WANG K, et al. Heterogeneous graph transformer[C]//Proceedings of the Web Conference 2020, 2020: 2704-2710.
[69] GONG J, TENG Z, TENG Q, et al. Hierarchical graph transformer-based deep learning model for large-scale multi-label text classification[J]. IEEE Access, 2020, 8: 30885-30896.
[70] ZHOU W N, ZHOU S D. Summary of model and applications of graph convolutional network[J]. Journal of Research in Science and Engineering, 2021, 3(1).
[71] LI Q, HAN Z, WU X M. Deeper insights into graph convolutional networks for semi-supervised learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
[72] YANG C, WANG R, YAO S, et al. Revisiting over-smoothing in deep GCNs[J]. arXiv:2003.13663, 2020.
[73] 徐冰冰, 岑科廷, 黄俊杰, 等. 图卷积神经网络综述[J]. 计算机学报, 2020, 43(5): 755-780.
XU B B, CEN K T, HUANG J J,et al.A survey on graph convolutional neural network[J], Chinese Journal of Computers, 2020, 43(5): 755-780.
[74] PAREJA A, DOMENICONI G, CHEN J, et al. EvolveGCN: evolving graph convolutional networks for dynamic graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 5363-5370.
[75] HAMILTON W, YING Z, LESKOVEC J. Inductive representation learning on large graphs[C]//Advances in Neural Information Processing Systems, 2017, 30.
[76] WANG H, ZHANG F, WANG J, et al. Exploring high-order user preference on the knowledge graph for recommender systems[J]. ACM Transactions on Information Systems (TOIS), 2019, 37(3): 1-26.