Abstract
Heterogeneous social events modeling in large and noisy data sources is an important task for applications such as international situation assessment and disaster relief. Accurate and interpretable classification can help human analysts better understand global social dynamics and make quick and accurate decisions. However, achieving these goals is challenging due to several factors: (i) it is not easy to model different types of objects and relations in heterogeneous events in an unified manner, (ii) it is difficult to extract different semantic dependences at different scales among word sequences, and (iii) it is hard to accurately learn the subtle difference between events. Recently, graph neural networks have demonstrated advantages in learning complex and heterogeneous data. In this paper, we design a social event modeling method based on a Heterogeneous Information Network (HIN) and meta-path to calculate the similarity of events. In order to extract different semantic dependence, we propose a multi-scales semantic feature extraction framework. We present a Local Extrema Graph convolution Network (LEGCN) to expand the difference of various types events achieving accurate classification. We conduct extensive experiments on multiple real-world datasets and show that the proposed method exhibits comparable or even superior performance and also provides convincing interpretation capabilities.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Cai, H., Zheng, V.W., Chang, K.C.C.: A comprehensive survey of graph embedding: problems, techniques, and applications. IEEE Trans. Knowl. Data Eng. 30(9), 1616–1637 (2018)
Chen, J., Ma, T., Xiao, C.: FastGCN: fast learning with graph convolutional networks via importance sampling. arXiv preprint arXiv:1801.10247 (2018)
Fouss, F., Pirotte, A., Renders, J.M., Saerens, M.: Random-walk computation of similarities between nodes of a graph with application to collaborative recommendation. IEEE Trans. Knowl. Data Eng. 19(3), 355–369 (2007)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lee, S., Park, S., Kahng, M., Lee, S.G.: PathRank: a novel node ranking measure on a heterogeneous graph for recommender systems. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management, pp. 1637–1641 (2012)
Ma, L., et al.: AdaCare: explainable clinical health status representation learning via scale-adaptive feature extraction and recalibration. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 825–832. AAAI Press (2020)
Meng, Y., Zhang, Y., Huang, J., Zhang, Y., Zhang, C., Han, J.: Hierarchical topic mining via joint spherical tree and text embedding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1908–1917 (2020)
Peng, H., Li, J., Gong, Q., Song, Y., Ning, Y., Lai, K., Yu, P.S.: Fine-grained event categorization with heterogeneous graph convolutional networks. arXiv preprint arXiv:1906.04580 (2019)
Ranjan, E., Sanyal, S., Talukdar, P.P.: Asap: adaptive structure aware pooling for learning hierarchical graph representations. In: AAAI, pp. 5470–5477 (2020)
Shi, C., Kong, X., Huang, Y., Philip, S.Y., Wu, B.: HeteSIM: a general framework for relevance measure in heterogeneous networks. IEEE Trans. Knowl. Data Eng. 26(10), 2479–2492 (2014)
Shi, C., Li, Y., Zhang, J., Sun, Y., Philip, S.Y.: A survey of heterogeneous information network analysis. IEEE Trans. Knowl. Data Eng. 29(1), 17–37 (2016)
Sun, Y., Han, J., Yan, X., Yu, P.S., Wu, T.: PathSIM: meta path-based top-k similarity search in heterogeneous information networks. Proc. VLDB Endow. 4(11), 992–1003 (2011)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
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)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Zhang, M., Wang, J., Wang, W.: HeteRank: a general similarity measure in heterogeneous information networks by integrating multi-type relationships. Inf. Sci. 453, 389–407 (2018)
Acknowledgements
This work was supported by the National Key Research and Development Program of China NO. 2017YFB0803301, and Postgraduate Scientific Research Innovation Project of Hunan Province CX20200015.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, H., Song, X., Liu, Y., Chen, C., Zhou, B. (2021). A Meta-path Based Graph Convolutional Network with Multi-scale Semantic Extractions for Heterogeneous Event Classification. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12712. Springer, Cham. https://doi.org/10.1007/978-3-030-75762-5_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-75762-5_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75761-8
Online ISBN: 978-3-030-75762-5
eBook Packages: Computer ScienceComputer Science (R0)