Skip to main content
SpringerLink
Log in

Forecasting traffic flow with spatial–temporal convolutional graph attention networks

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Traffic flow prediction is crucial for intelligent transportation system, such as traffic management, congestion alleviation and public risk assessment. Recently, attention mechanism and deep neural networks are utilized to capture traffic dependencies. However, two challenges have yet to be well addressed: (i) previous works overlook the global dependencies across different regions; (ii) how to integrate spatial and temporal information aggregation with latent channel-aware semantics. To tackle these issues, we propose a deep spatial–temporal convolutional graph attention network for citywide traffic flow prediction. We first apply the multi-resolution transformer network to capture traffic dependencies among different regions with the encoding of multi-level periodicity. Spatial dependencies are captured by the attentive graph neural networks followed by convolutional networks from local view to global view. We further propose to inject spatial contextual signals into our framework with the designed channel-aware recalibration residual network, which effectively endows model with the capability of mapping spatial–temporal data patterns into different representation subspaces of latent semantics. The extensive experiments on four real-world datasets demonstrate at least 5% performance gain of our framework by comparing with 19 state-of-the-art traffic prediction methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Yang D, Qu B, Yang J et al (2020) LBSN2Vec++: heterogeneous hypergraph embedding for location-based social networks. Trans Knowl Data Eng (TKDE) 34:1843–1855

    Google Scholar 

  2. Ding Jingtao, Yu Guanghui, Li Yong, Jin Depeng, Gao Hui (2019) Learning from hometown and current city: cross-city POI recommendation via interest drift and transfer learning. In: international conference on interactive, mobile, wearable and ubiquitous technologies (Ubicomp), 3. 1–28

  3. Cui Z, Henrickson K, Ke R, Wang Y (2020) Traffic graph convolutional recurrent neural network: a deep learning framework for network-scale traffic learning and forecasting. Trans Intell Transp Syst (TITS) 21(11):4883–4894

    Article  Google Scholar 

  4. Pan Z, Liang Y, Wang W, Yu Y, Zheng Y, Zhang J (2019) Urban traffic prediction from spatio-temporal data using deep meta learning. In: international conference on knowledge discovery and data mining (KDD), ACM

  5. Yang D, Qu B, Yang J (2019) Cudre-Mauroux, Philippe, revisiting user mobility and social relationships in lbsns: a hypergraph embedding approach. In: the web conference (WWW) pp. 2147–2157

  6. Zhang Y, Zhang Y, Su R (2019) Pedestrian-safety-aware traffic light control strategy for urban traffic congestion alleviation. Trans Intell Transp Syst (TITS) 22(1):178–193

    Article  MathSciNet  Google Scholar 

  7. Huaxiu Y, Xianfeng T, Hua W, and others (2019) Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction. In: international conference on artificial intelligence (AAAI)

  8. Junbo Z, Yu Z, Dekang Q (2017) Deep spatio-temporal residual networks for citywide crowd flows prediction. In: international conference on artificial intelligence (AAAI)

  9. Wang X, Ji H, Shi C, Wang B, Ye Y, Cui P, Yu PS (2019) Heterogeneous graph attention network. In: the web conference (WWW), pp. 165–174

  10. Sun J, Zhang J, Li Q, Yi X, Liang Y, Zheng Y (2020) Predicting citywide crowd flows in irregular regions using multi-view graph convolutional networks. Trans Knowl Data Eng (TKDE) 34:2348–2359

    Article  Google Scholar 

  11. Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: international joint conferences on artificial intelligence (IJCAI)

  12. Li Y, Yu R, Shahabi C, Liu Y (2018) Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: international conference on learning representations (ICLR)

  13. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: international conference on learning representations (ICLR)

  14. Yao H, Wu F, Ke J, Tang X, and others (2018) Deep multi-view spatial-temporal network for taxi demand prediction. In: international conference on artificial intelligence (AAAI), pp. 2588–2595

  15. Geng X, Li Y, Wang L, Zhang L, Yang Q, Ye J, Liu Y (2019) Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In: international conference on artificial intelligence (AAAI)

  16. Shen B, Liang X, Ouyang Y, Liu M, and others (2018) In: international conference on knowledge discovery and data mining (KDD), pp. 724–733

  17. Wu X, Shi B, Dong Y, Huang C, Faust L, Chawla NV (2018) Restful: resolution-aware forecasting of behavioral time series data. In: international conference on information and knowledge management (CIKM), pp. 1073–1082

  18. Pan B, Demiryurek U, and others (2012) Utilizing real-world transportation data for accurate traffic prediction. In: international conference on data mining (ICDM), pp. 595–604

  19. Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. Trans Intell Syst Technol (TIST) 2(3):1–27

    Article  Google Scholar 

  20. Srinivasan D, Chan CW, Balaji PG (2009) Computational intelligence-based congestion prediction for a dynamic urban street network. Neurocomputing 72:2710–2716

    Article  Google Scholar 

  21. Liu Q, Wu S, Wang L, (2016) Predicting the next location: a recurrent model with spatial and temporal contexts. In: international conference on artificial tntelligence (AAAI), pp. 194–200

  22. Yu R, Li Y, Shahabi C, Demiryurek U, Liu Y (2017) Deep learning: a generic approach for extreme condition traffic forecasting. In: SIAM international conference on data mining (SDM), pp. 777–785

  23. Zhang J, Zheng Y, Qi D (2017) Deep spatio-temporal residual networks for citywide crowd flows prediction. In: international conference on artificial intelligence (AAAI)

  24. Zhang J, Zheng Y, Qi D, (2016) DNN-based prediction model for spatio-temporal data. In: international conference on advances in geographic information systems (SIGSPATIAL), pp. 1–4

  25. Zheng H, Lin F, Feng X, Chen Y (2020) A hybrid deep learning model with attention-based conv-lstm networks for short-term traffic flow prediction. Trans Intell Transp Syst (TITS) 22(11):6910–6920

    Article  Google Scholar 

  26. Liang Y, Ouyang K, Jing L, Ruan S, Liu Y, Zhang J, Rosenblum DS, Zheng Y (2019) UrbanFM: inferring fine-grained urban flows. In: international conference on knowledge discovery and data mining (KDD), pp. 3132–3142

  27. Ying Z, Bourgeois D, You J, Zitnik M, Leskovec J (2019) Gnnexplainer: generating explanations for graph neural networks. Neural Inf Process Syst (NeurIPS), pp. 9244–9255

  28. Fu X, Zhang J, Meng Z, King I (2020) MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. In: the web conference (WWW), pp. 2331–2341

  29. Wang X, He X, Wang M, Feng F, Chua TS (2019) Neural graph collaborative filtering. In: international conference on research and development in information retrieval (SIGIR), pp. 165–174

  30. Fan W, Ma Y, Li Q, He Y, Zhao E, Tang J, Yin D (2019) Graph neural networks for social recommendation. In: the web conference (WWW), pp. 417–426

  31. Song C, Lin Y, Guo S, Wan H (2020) Spatial-temporal synchronous graph convolutional networks: a new framework for spatial-temporal network data forecasting. In: international conference on artificial intelligence (AAAI), vol 34, pp. 914–921

  32. Zhao L, Song Y, Zhang C, Liu Y, Wang P, Tao Lin et al (2019) T-gcn: a temporal graph convolutional network for traffic prediction. Trans Intell Transp Syst (TITS) 21(9):3848–3858

    Article  Google Scholar 

  33. Yuan Z, Liu H, Liu Y, Zhang D, Yi F, Zhu N, Xiong H (2020) Spatio-temporal dual graph attention network for query-POI matching. In: international conference on research and development in information retrieval (SIGIR), pp. 629–638

  34. Zheng C, Fan X, Wang C, Qi J (2020) Gman: a graph multi-attention network for traffic prediction. In: international conference on artificial intelligence (AAAI), pp. 1234–1241

  35. Zhang B, Xiong D, Xie J, Su J (2020) Neural machine translation with GRU-gated attention model. Trans Neural Netw Learn Syst (TNNLS) 31(11):4688–4698

    Article  Google Scholar 

  36. Lim N, Hooi B, Ng SK, Wang X, Goh YL, Weng R, Varadarajan J (2020) STP-UDGAT: spatial-temporal-preference user dimensional graph attention network for next POI recommendation. In: international conference on information and knowledge management (CIKM), pp. 845–854

  37. Feng J, Li Y, Zhang C, Sun F, Meng F, Guo A, Jin D (2018) Deepmove: predicting human mobility with attentional recurrent networks. In: the web conference (WWW), pp. 1459–1468, ACM

  38. Xu F, Li Y, Xu S (2020) Attentional multi-graph convolutional network for regional economy prediction with open migration data. In: international conference on knowledge discovery and data mining (KDD), pp. 2225–2233

  39. Gao Q, Zhou F, Trajcevski G, Zhang K, Zhong T, Zhang F (2019) Predicting human mobility via variational attention. In: the web conference (WWW), pp. 2750–2756

  40. Zhang X, Huang C, Xu Y, Xia L (2020) Spatial-temporal convolutional graph attention networks for citywide traffic flow forecasting. In: international conference on information and knowledge management (CIKM)

  41. Zhang X, Huang C, Xu Y, Xia L, and others (2021) Traffic flow forecasting with spatial-temporal graph diffusion network. In: international conference on artificial intelligence (AAAI)

  42. Ma X, Zhang P, Zhang S, Duan N, Hou Y et al (2019) A tensorized transformer for language modeling. Neural Inf Process Syst (NeurIPS) 32:2232–2242

    Google Scholar 

  43. Wu X, Huang C, Zhang C, Chawla NV (2020) Hierarchically structured transformer networks for fine-grained spatial event forecasting. In: the web conference (WWW), pp. 2320–2330

  44. Al-Rfou R, Choe D, Constant N, and others (2019) Character-level language modeling with deeper self-attention. In: international conference on artificial intelligence (AAAI), vol 33, pp. 3159–3166

  45. Knyazev B, Taylor GW, Amer M (2019) Understanding attention and generalization in graph neural networks. Neural Inf Process Syst (NeurIPS) 32:4202–4212

    Google Scholar 

  46. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Neural Inf Process Syst (NeurIPS) 30:5998–6008

    Google Scholar 

  47. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: conference on computer vision and pattern recognition (CVPR), pp. 770–778

  48. Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv preprint arXiv:1607.06450

  49. Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: international conference on learning representations (ICLR)

  50. Wang F, Jiang M, Qian C, Yang S, Li C, and others (2017) Residual attention network for image classification. In: conference on computer vision and pattern recognition (CVPR), pp. 3156–3164

  51. Chen C, Li K, Teo SG, Zou X, Wang K, Wang J, Zeng Z (2019) Gated residual recurrent graph neural networks for traffic prediction. In: international conference on artificial intelligence (AAAI), vol 33, pp. 485–492

  52. Grover A, Leskovec J (2016) node2vec: scalable feature learning for networks. In: international conference on knowledge discovery and data mining (KDD), pp. 855–864

Download references

Author information

Authors and Affiliations

  1. South China University of Technology, Guangzhou, China

    Xiyue Zhang, Yong Xu & Yizhen Shao

Authors
  1. Xiyue Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yizhen Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiyue Zhang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, X., Xu, Y. & Shao, Y. Forecasting traffic flow with spatial–temporal convolutional graph attention networks. Neural Comput & Applic 34, 15457–15479 (2022). https://doi.org/10.1007/s00521-022-07235-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07235-z

Keywords

Search

Navigation