Abstract
Recently, the remarkable effect of applying Dynamic Graph Neural Networks (DGNNs) to traffic speed prediction has received wide attention. Existing DGNN-based researches usually use a pre-defined or an adaptive matrix to capture the spatial correlations in traffic data. However, these static matrices are not enough to match the dynamic characteristics of spatial correlations. We argue that the global changes and local fluctuations of spatial correlations are dynamic with different frequencies. To this end, in this paper, we propose a Two-Tower DGNN (T\(^{2}\)-GNN) framework which divides the traffic data into a seasonal static component and an acyclic dynamic component, thus enhancing traffic speed prediction. The two components generated by an auto-decomposing block reflect global changes and local fluctuations of spatial correlations, respectively. Moreover, we use two parallel dynamic graph generation layers to construct a seasonal graph and an acyclic graph at each time step. In this way, the high-level representations of these two kinds of dynamic changes are learned through two dynamic graph convolution layers. Besides, the impact of fixed road network structure is modeled on the pre-defined graph and added to the spatial correlations. And we capture temporal correlations in temporal block before modeling spatial correlations. Finally, skip connections are used to converge the spatial-temporal correlations for final prediction. Experimental results on an urban dataset and two highway datasets show our proposed framework achieves the state-of-the-art prediction performances in terms of Mean Average Error (MAE) and Root Mean Squared Error (RMSE).
This work is supported by the China Postdoctoral Science Foundation (Grant No. 2021M693101).
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
Bruna, J., Zaremba, W., Szlam, A., et al.: Spectral networks and locally connected networks on graphs. In: ICLR 2014 (2014)
Diao, Z., Wang, X., Zhang, D., et al.: Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting. In: AAAI 2019, pp. 890–897 (2019)
Ermagun, A., Levinson, D.: Spatiotemporal traffic forecasting: review and proposed directions. Transp. Rev. 38(6), 786–814 (2018)
Fang, S., Zhang, Q., Meng, G., et al.: GstNET: global spatial-temporal network for traffic flow prediction. In: IJCAI, pp. 2286–2293 (2019)
Guo, S., Lin, Y., Feng, N., et al.: Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: AAAI 2019, pp. 922–929 (2019)
Han, L., Du, B., Sun, L., et al.: Dynamic and multi-faceted spatio-temporal deep learning for traffic speed forecasting. In: SIGKDD 2021, pp. 547–555 (2021)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: PMLR 2015, pp. 448–456 (2015)
Jeong, Y.S., Byon, et al.: Supervised weighting-online learning algorithm for short-term traffic flow prediction. IEEE Trans. Intell. Transp. Syst. 14(4), 1700–1707 (2013)
Kumar, S.V., Vanajakshi, L.: Short-term traffic flow prediction using seasonal ARIMA model with limited input data. Eur. Transp. Res. Rev. 7(3), 1–9 (2015)
Li, Y., Yu, R., Shahabi, et al.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: ICLR 2018 (2018)
Li, Z., Li, et al.: A two-stream graph convolutional neural network for dynamic traffic flow forecasting. In: ICTAI 2020, pp. 355–362 (2020)
Pan, Z., Liang, et al.: Urban traffic prediction from spatio-temporal data using deep meta learning. In: SIGKDD 2019, pp. 1720–1730 (2019)
Sutskever, I., Vinyals, et al.: Sequence to sequence learning with neural networks. In: NIPS 2014, pp. 3104–3112 (2014)
Wang, X., Ma, et al.: Traffic flow prediction via spatial temporal graph neural network. In: WWW 2020, pp. 1082–1092 (2014)
Wu, Z., Pan, et al.: Connecting the dots: Multivariate time series forecasting with graph neural networks. In: SIGKDD 2020, pp. 753–763 (2020)
Wu, Z., Pan, et al.: Graph wavenet for deep spatial-temporal graph modeling. In: IJCAI 2019, pp 1907–1913 (2019)
Yao, H., Wu, et al.: Deep multi-view spatial-temporal network for taxi demand prediction. In: AAAI 2018, pp. 2588–2595 (2018)
Yu, B., Yin, et al.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: IJCAI 2018, pp. 3634–3640 (2018)
Zhang, J., Zheng, et al.: Deep spatio-temporal residual networks for citywide crowd flows prediction. In: AAAI 2017, pp. 1655–1661 (2017)
Zhang, J., Zheng, Y., Qi, D., Li, R., Yi, X., Li, T.: Predicting citywide crowd flows using deep spatio-temporal residual networks. Artif. Intell. 259, 147–166 (2018)
Zhang, Q., Chang, et al.: Spatio-temporal graph structure learning for traffic forecasting. In: AAAI 2020, pp. 1177–1185 (2020)
Zhao, L., Song, et al.: T-GCN: A temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848–3858 (2020)
Zheng, C., Fan, et al.: GMAN: a graph multi-attention network for traffic prediction. In: AAAI 2020, pp. 1234–1241 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shen, Y., Li, L., Xie, Q., Li, X., Xu, G. (2022). A Two-Tower Spatial-Temporal Graph Neural Network for Traffic Speed Prediction. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)