Abstract
Traffic forecasting is crucial for location-based services. Recent studies tend to utilize dynamic graph neural networks to capture spatial-temporal correlations. However, urban traffic faces spatial heterogeneity of different lane structure at intersections, leading to different traffic patterns of lanes in different directions. It also confronts temporal heterogeneity of varying traffic trends in different time periods. Unfortunately, the influence of such spatial-temporal heterogeneity on traffic evolution are not fully considered in existing methods. To this end, this paper proposes a novel dynamic-graph-based model called HA-STGN, which integrates these heterogeneous features into spatial-learning components to model traffic networks in a finer granularity. Specifically, we design a dynamic graph model, which performs on a direction-aware road network to extract the structural information of intersections. Then, a time-sensitive attention mechanism is proposed to perceive the effect of time by introducing explicit temporal features. Moreover, an adaptive fusion module is provided to balance the spatial-temporal information adaptively. Finally, extensive experiments are conducted on two real-world datasets to verify the effectiveness of our model. The results show that our proposed HA-STGN can effectively capture spatial-temporal dependencies and outperform all the baseline methods.
Similar content being viewed by others
References
Bai, L., Yao, L., Li, C., Wang, X., Wang, C.: Adaptive graph convolutional recurrent network for traffic forecasting. In: NeurIPS, pp. 1–12 (2020). https://proceedings.neurips.cc/paper/2020/hash/ce1aad92b939420fc17005e5461e6f48-Abstract.html
Box, G.E.P., Jenkins, G.M.: Time series analysis : forecasting and control. Journal of Time 31(3), 546–549 (2010). https://doi.org/10.1111/j.1467-9892.2009.00643.x
Chandra, S.R., Al-Deek, H.: Predictions of freeway traffic speeds and volumes using vector autoregressive models. J. Intell. Transp. Syst. 13(2), 53–72 (2009). https://doi.org/10.1080/15472450902858368
Chen, L., Shang, S., Guo, T.: Real-time route search by locations. In: AAAI, pp. 574–581 (2020). https://doi.org/10.1609/aaai.v34i01.5396
Chen, L., Shang, S., Jensen, C.S., Yao, B., Zhang, Z., Shao, L.: Effective and efficient reuse of past travel behavior for route recommendation. In: KDD, pp. 488–498 (2019). https://doi.org/10.1145/3292500.3330835
Chen, L., Shang, S., Yao, B., Li, J.: Pay your trip for traffic congestion: Dynamic pricing in traffic-aware road networks. In: AAAI, pp. 582–589 (2020). https://doi.org/10.1609/aaai.v34i01.5397
Chen, H., Yin, H., Sun, X., Chen, T., Gabrys, B., Musial, K.: Multi-level graph convolutional networks for cross-platform anchor link prediction. In: KDD, pp. 1503–1511 (2020). https://doi.org/10.1145/3394486.3403201
Chen, Z., Yao, B., Wang, Z., Gao, X., Shang, S., Ma, S., Guo, M.: Flexible aggregate nearest neighbor queries and its keyword-aware variant on road networks. IEEE Trans. Knowl. Data Eng. 33(12), 3701–3715 (2021). https://doi.org/10.1109/TKDE.2020.2975998
Dauphin, Y.N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. In: ICML. Proceedings of Machine Learning Research, vol. 70, pp. 933–941 (2017). http://proceedings.mlr.press/v70/dauphin17a.html
Guo, S., Lin, Y., Feng, N., Song, C., Wan, H.: Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: AAAI, pp. 922–929 (2019). https://doi.org/10.1609/aaai.v33i01.3301922
Han, P., Li, Z., Liu, Y., Zhao, P., Li, J., Wang, H., Shang, S.: Contextualized point-of-interest recommendation. In: IJCAI, pp. 2484–2490 (2020). https://doi.org/10.24963/ijcai.2020/344
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Hong, H., Lin, Y., Yang, X., Li, Z., Fu, K., Wang, Z., Qie, X., Ye, J.: Heteta: Heterogeneous information network embedding for estimating time of arrival. In: KDD, pp. 2444–2454 (2020). https://doi.org/10.1145/3394486.3403294
Hui, B., Yan, D., Chen, H., Ku, W.: Trajnet: A trajectory-based deep learning model for traffic prediction. In: KDD, pp. 716–724 (2021). https://doi.org/10.1145/3447548.3467236
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, pp. 1–15 (2015). arxiv:1412.6980
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (Poster), pp. 1–14 (2017). https://openreview.net/forum?id=SJU4ayYgl
Li, K., Chen, L., Shang, S., Kalnis, P., Yao, B.: Traffic congestion alleviation over dynamic road networks: Continuous optimal route combination for trip query streams. In: IJCAI, pp. 3656–3662 (2021). https://doi.org/10.24963/ijcai.2021/503
Li, K., Chen, L., Shang, S.: Towards alleviating traffic congestion: Optimal route planning for massive-scale trips. In: IJCAI, pp. 3400–3406 (2020). https://doi.org/10.24963/ijcai.2020/470
Li, Y., Fu, K., Wang, Z., Shahabi, C., Ye, J., Liu, Y.: Multi-task representation learning for travel time estimation. In: KDD, pp. 1695–1704 (2018). https://doi.org/10.1145/3219819.3220033
Li, X., Shang, Y., Cao, Y., Li, Y., Tan, J., Liu, Y.: Type-aware anchor link prediction across heterogeneous networks based on graph attention network. In: AAAI, pp. 147–155 (2020). https://aaai.org/ojs/index.php/AAAI/article/view/5345
Li, M., Tong, P., Li, M., Jin, Z., Huang, J., Hua, X.: Traffic flow prediction with vehicle trajectories. In: AAAI, pp. 294–302 (2021). https://ojs.aaai.org/index.php/AAAI/article/view/16104
Li, R., Wang, S., Zhu, F., Huang, J.: Adaptive graph convolutional neural networks. In: AAAI, pp. 3546–3553 (2018). https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16642
Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In: ICLR (Poster) (2018). https://openreview.net/forum?id=SJiHXGWAZ
Li, Y., Li, K., Chen, C., Zhou, X., Zeng, Z., Li, K.: Modeling temporal patterns with dilated convolutions for time-series forecasting. ACM Trans. Knowl. Discov. Data 16(1), 14–11422 (2022). https://doi.org/10.1145/3453724
Lin, Z., Feng, J., Lu, Z., Li, Y., Jin, D.: Deepstn+: Context-aware spatial-temporal neural network for crowd flow prediction in metropolis. In: AAAI, pp. 1020–1027 (2019). https://doi.org/10.1609/aaai.v33i01.33011020
Lv, Z., Xu, J., Zheng, K., Yin, H., Zhao, P., Zhou, X.: LC-RNN: A deep learning model for traffic speed prediction. In: IJCAI, pp. 3470–3476 (2018). https://doi.org/10.24963/ijcai.2018/482
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphsx. In: ICML. JMLR Workshop and Conference Proceedings, vol. 48, pp. 2014–2023 (2016). http://proceedings.mlr.press/v48/niepert16.html
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: CIKM, pp. 2683–2691 (2019). https://doi.org/10.1145/3357384.3357832
Seo, Y., Defferrard, M., Vandergheynst, P., Bresson, X.: Structured sequence modeling with graph convolutional recurrent networks. In: ICONIP (1). Lecture Notes in Computer Science, vol. 11301, pp. 362–373 (2018). https://doi.org/10.1007/978-3-030-04167-0_33
Shang, S., Chen, L., Jensen, C.S., Wen, J., Kalnis, P.: Searching trajectories by regions of interest. In: ICDE, pp. 1741–1742 (2018). https://doi.org/10.1109/ICDE.2018.00228
Shang, S., Ding, R., Zheng, K., Jensen, C.S., Kalnis, P., Zhou, X.: Personalized trajectory matching in spatial networks. VLDB J. 23(3), 449–468 (2014). https://doi.org/10.1007/s00778-013-0331-0
Shi, X., Gao, Z., Lausen, L., Wang, H., Yeung, D., Wong, W., Woo, W.: Deep learning for precipitation nowcasting: A benchmark and A new model. In: NIPS, pp. 5617–5627 (2017). https://proceedings.neurips.cc/paper/2017/hash/a6db4ed04f1621a119799fd3d7545d3d-Abstract.html
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. arxiv:1710.10903, 1–12 (2017)
Wang, Z., Wang, J., Guo, Y., Gong, Z.: Zero-shot node classification with decomposed graph prototype network. In: KDD, pp. 1769–1779 (2021). https://doi.org/10.1145/3447548.3467230
Wang, F., Xu, J., Liu, C., Zhou, R., Zhao, P.: MTGCN: A multitask deep learning model for traffic flow prediction. In: DASFAA, vol. 12112, pp. 435–451 (2020). https://doi.org/10.1007/978-3-030-59410-7_30
Wang, F., Xu, J., Liu, C., Zhou, R., Zhao, P.: On prediction of traffic flows in smart cities: a multitask deep learning based approach. World Wide Web 24(3), 805–823 (2021). https://doi.org/10.1007/s11280-021-00877-4
Williams, B.M., Hoel, L.A.: Modeling and forecasting vehicular traffic flow as a seasonal arima process: Theoretical basis and empirical results. Journal of Transportation Engineering 129(6), 664–672 (2003). https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664)
Wu, J., He, J., Xu, J.: Demo-net: Degree-specific graph neural networks for node and graph classification. In: KDD, pp. 406–415 (2019). https://doi.org/10.1145/3292500.3330950
Wu, Z., Pan, S., Long, G., Jiang, J., Zhang, C.: Graph wavenet for deep spatial-temporal graph modeling. In: IJCAI, pp. 1907–1913 (2019). https://doi.org/10.24963/ijcai.2019/264
Wu, C., Ho, J., Lee, D.: Travel-time prediction with support vector regression. IEEE Trans. Intell. Transp. Syst. 5(4), 276–281 (2004). https://doi.org/10.1109/TITS.2004.837813
Xu, S., Zhang, R., Cheng, W., Xu, J.: Mtlm: a multi-task learning model for travel time estimation. GeoInformatica 1, 1–17 (2020). https://doi.org/10.1007/s10707-020-00422-x
Xu, J., Zhao, J., Zhou, R., Liu, C., Zhao, P., Zhao, L.: Predicting destinations by a deep learning based approach. IEEE Trans. Knowl. Data Eng. 33(2), 651–666 (2021). https://doi.org/10.1109/TKDE.2019.2932984
Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In: IJCAI, pp. 3634–3640 (2018). https://doi.org/10.24963/ijcai.2018/505
Yuan, C., Chakraborty, A.: Deep convolutional factor analyser for multivariate time series modeling. In: ICDM, pp. 1323–1328 (2016). https://doi.org/10.1109/ICDM.2016.0180
Yuan, H., Li, G., Bao, Z., Feng, L.: Effective travel time estimation: When historical trajectories over road networks matter. In: SIGMOD Conference, pp. 2135–2149 (2020). https://doi.org/10.1145/3318464.3389771
Zhang, J., Zheng, Y., Qi, D.: Deep spatio-temporal residual networks for citywide crowd flows prediction. In: AAAI, pp. 1655–1661 (2017). http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14501
Zhao, L., Song, Y., Zhang, C., Liu, Y., Wang, P., Lin, T., Deng, M., Li, H.: T-GCN: A temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848–3858 (2020). https://doi.org/10.1109/TITS.2019.2935152
Zheng, C., Fan, X., Wang, C., Qi, J.: GMAN: A graph multi-attention network for traffic prediction. In: AAAI, pp. 1234–1241 (2020). https://aaai.org/ojs/index.php/AAAI/article/view/5477
Zheng, Z., Su, D.: Short-term traffic volume forecasting: A k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm. Transportation Research Part C Emerging Technologies 43, 143–157 (2014). https://doi.org/10.1016/j.trc.2014.02.009
Zhou, F., Cao, C., Zhang, K., Trajcevski, G., Zhong, T., Geng, J.: Meta-gnn: On few-shot node classification in graph meta-learning. In: CIKM, pp. 2357–2360 (2019). https://doi.org/10.1145/3357384.3358106
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant Nos. 61872258, 61772356, 61876117, and 61802273.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflicts of interest
We declare that the named authors have no any conflict of interest.
Additional information
This article belongs to the Topical Collection: Special Issue on Spatiotemporal Data Management and Analytics for Recommend
Guest Editors: Shuo Shang, Xiangliang Zhang and Panos Kalnis.
Rights and permissions
About this article
Cite this article
Xu, M., Li, X., Wang, F. et al. Learning to effectively model spatial-temporal heterogeneity for traffic flow forecasting. World Wide Web 26, 849–865 (2023). https://doi.org/10.1007/s11280-022-01045-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11280-022-01045-y