Abstract
Graph convolutional network (GCN) has shown promising performance on the text classification tasks via modeling irregular correlations between word and document. There are multiple correlations within a text graph adjacency matrix, including word-word, word-document, and document-document, so we regard it as heterogeneous. While existing graph convolutional filters are constructed based on homogeneous information diffusion processes, which may not be appropriate to the heterogeneous graph. This paper proposes an expressive and efficient circulant tensor graph convolutional network (CTGCN). Specifically, we model a text graph into a multi-dimension tensor, which characterizes three types of homogeneous correlations separately. CTGCN constructs an expressive and efficient tensor filter based on the t-product operation, which designs a t-linear transformation in the tensor space with a block circulant matrix. Tensor operation t-product effectively extracts high-dimension correlation among heterogeneous feature spaces, which is customarily ignored by other GCN-based methods. Furthermore, we introduce a heterogeneity attention mechanism to obtain more discriminative features. Eventually, we evaluate our proposed CTGCN on five publicly used text classification datasets, extensive experiments demonstrate the effectiveness of the proposed model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bastings, J., Titov, I., Aziz, W., Marcheggiani, D., Sima’an, K.: Graph convolutional encoders for syntax-aware neural machine translation. arXiv preprint arXiv:1704.04675 (2017)
Braman, K.: Third-order tensors as linear operators on a space of matrices. Linear Algebra Appl. 433(7), 1241–1253 (2010)
Bruna, J., Zaremba, W., Szlam, A., Lecun, Y.: Spectral networks and locally connected networks on graphs. Comput. Sci. (2014)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, pp. 3844–3852 (2016)
Feldman, R.: Techniques and applications for sentiment analysis. Commun. ACM 56(4), 82–89 (2013)
Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 (2015)
Huang, Z., Chung, W., Ong, T.H., Chen, H.: A graph-based recommender system for digital library. In: Proceedings of the 2nd ACM/IEEE-CS Joint Conference on Digital Libraries, pp. 65–73. ACM (2002)
Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)
Kiers, H.A., Mechelen, I.V.: Three-way component analysis: principles and illustrative application. Psychol. Methods 6(1), 84 (2001)
Kilmer, M.E., Braman, K., Hao, N., Hoover, R.C.: Third-order tensors as operators on matrices: a theoretical and computational framework with applications in imaging. SIAM J. Matrix Anal. Appl. 34(1), 148–172 (2013)
Kilmer, M.E., Martin, C.D.: Factorization strategies for third-order tensors. Linear Algebra Appl. 435(3), 641–658 (2011)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188–1196 (2014)
Linmei, H., Yang, T., Shi, C., Ji, H., Li, X.: Heterogeneous graph attention networks for semi-supervised short text classification. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 4823–4832 (2019)
Litvak, M., Last, M.: Graph-based keyword extraction for single-document summarization. In: Proceedings of the workshop on Multi-source Multilingual Information Extraction and Summarization, pp. 17–24. Association for Computational Linguistics (2008)
Liu, P., Qiu, X., Huang, X.: Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101 (2016)
Liu, X., You, X., Zhang, X., Wu, J., Lv, P.: Tensor graph convolutional networks for text classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 8409–8416 (2020)
Luo, Y., Uzuner, Ö., Szolovits, P.: Bridging semantics and syntax with graph algorithms-state-of-the-art of extracting biomedical relations. Brief. Bioinform. 18(1), 160–178 (2017)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)
Newman, E., Horesh, L., Avron, H., Kilmer, M.: Stable tensor neural networks for rapid deep learning. arXiv preprint arXiv:1811.06569 (2018)
Peng, H., et al.: Large-scale hierarchical text classification with recursively regularized deep graph-CNN. In: Proceedings of the 2018 World Wide Web Conference on World Wide Web, pp. 1063–1072. International World Wide Web Conferences Steering Committee (2018)
Ragesh, R., Sellamanickam, S., Iyer, A., Bairi, R., Lingam, V.: Hetegcn: heterogeneous graph convolutional networks for text classification. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 860–868 (2021)
Ramos, J., et al.: Using TF-IDF to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning, vol. 242, pp. 133–142. Piscataway, NJ (2003)
Shen, D., et al.: Baseline needs more love: On simple word-embedding-based models and associated pooling mechanisms. arXiv preprint arXiv:1805.09843 (2018)
Tang, J., Qu, M., Mei, Q.: PTE: predictive text embedding through large-scale heterogeneous text networks. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1165–1174. ACM (2015)
Wang, S., Manning, C.D.: Baselines and bigrams: simple, good sentiment and topic classification. In: Proceedings of the 50th annual meeting of the association for computational linguistics: short papers-volume 2, pp. 90–94. Association for Computational Linguistics (2012)
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
Wyle, M.: A wide area network information filter. In: Proceedings First International Conference on Artificial Intelligence Applications on Wall Street, pp. 10–15. IEEE (1991)
Yao, L., Mao, C., Luo, Y.: Graph convolutional networks for text classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7370–7377 (2019)
Zhang, X., Zhang, T., Zhao, W., Cui, Z., Yang, J.: Dual-attention graph convolutional network. In: Palaiahnakote, S., Sanniti di Baja, G., Wang, L., Yan, W.Q. (eds.) ACPR 2019. LNCS, vol. 12047, pp. 238–251. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-41299-9_19
Zhou, P., Qi, Z., Zheng, S., Xu, J., Bao, H., Xu, B.: Text classification improved by integrating bidirectional LSTM with two-dimensional max pooling. arXiv preprint arXiv:1611.06639 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, X., Zhang, T., Xu, C., Cui, Z. (2022). Circulant Tensor Graph Convolutional Network for Text Classification. In: Wallraven, C., Liu, Q., Nagahara, H. (eds) Pattern Recognition. ACPR 2021. Lecture Notes in Computer Science, vol 13188. Springer, Cham. https://doi.org/10.1007/978-3-031-02375-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-02375-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02374-3
Online ISBN: 978-3-031-02375-0
eBook Packages: Computer ScienceComputer Science (R0)