Abstract
Traffic flow forecasting is crucial for traffic management, but the complex spatio-temporal correlation and heterogeneity among traffic nodes make this problem challenging. While many deep spatio-temporal models have been proposed and applied to traffic flow prediction, they mostly focus on capturing the spatio-temporal correlation among traffic nodes, ignoring the influence of the functional characteristics of the area to which the nodes belong. Therefore, there is a need to propose a method to help models capture such influence. This paper presents a novel framework that enhances existing deep spatio-temporal models by combining clustering with heterogeneous graph neural networks. Our framework’s clustering module measures the similarity between nodes in the traffic pattern using the Dynamic Time Warping and the Wasserstein distance and then applies spectral clustering to divide the nodes into different clusters based on traffic pattern. Our graph transformer module can adaptively construct a new graph for nodes in the same cluster, and the spatio-temporal feature learning module captures the spatio-temporal correlation among nodes based on the new graph. Extensive experiments on two real datasets demonstrate that our proposed framework can effectively improve the performance of some representative deep spatio-temporal models.
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
References
Luo, Q.: Research on intelligent transportation system technologies and applications. In: 2008 Workshop on Power Electronics and Intelligent Transportation System, Piscataway, pp. 529–531. IEEE (2008)
Jiang, W., Luo, J.: Graph neural network for traffic forecasting: a survey. Expert Syst. Appl. 117921 (2022)
Pan, Z., Wang, Z., Wang, W., Yu, Y., Zhang, J., Zheng, Y.: Matrix factorization for spatio-temporal neural networks with applications to urban flow prediction. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 2683–2691. ACM, New York (2019)
Li, M., Zhu, Z.: Spatial-temporal fusion graph neural networks for traffic flow forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, Menlo Park, vol. 35, pp. 4189–4196. AAAI (2021)
Cai, X., Dai, G., Yang, L.: Survey on spectral clustering algorithms. Comput. Sci. 35(7), 14–18 (2008)
Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Advances in Neural Information Processing Systems, vol. 14 (2001)
Wang, X., et al.: Heterogeneous graph attention network. In: The World Wide Web Conference, pp. 2022–2032. ACM, New York (2019)
Yun, S., Jeong, M., Kim, R., Kang, J., Kim, H.J.: Graph transformer networks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, Menlo Park, vol. 15, pp. 359–370. AAAI (1994)
Panaretos, V.M., Zemel, Y.: Statistical aspects of Wasserstein distances. Annu. Rev. Stat. Appl. 6, 405–431 (2019)
Liu, J., Guan, W.: A summary of traffic flow forecasting methods. J. Highway Transp. Res. Dev. 21(3), 82–85 (2004)
Box, G.E.P., Pierce, D.A.: Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. J. Am. Stat. Assoc. 65(332), 1509–1526 (1970)
Cho, K., van Merriënboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder–decoder approaches. In: Syntax, Semantics and Structure in Statistical Translation, vol. 103 (2014)
Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: International Conference on Learning Representations (2018)
Zhao, L., et al.: T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848–3858 (2019)
Guo, S., Lin, Y., Feng, N., Song, C., Wan, H.: Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, Menlo Park, vol. 33, pp. 922–929. AAAI (2019)
Zhang, J., Liu, Y., Gui, Y., Ruan, C.: An improved model combining outlook attention and graph embedding for traffic forecasting. Symmetry 15(2), 312 (2023)
Acknowledgements
This project is supported by Natural Science Foundation of Shandong Province for Key Project (No. ZR2020KF006), National Natural Science Foundation of China (No. 62273164) and A Project of Shandong Province Higher Educational Science and Technology Program (No. J16LB06, No. J17KA055).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Luo, L., Han, S., Li, Z., Yang, J., Yang, X. (2023). A Traffic Flow Prediction Framework Based on Clustering and Heterogeneous Graph Neural Networks. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_5
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)