Skip to main content
SpringerLink
Log in

A self-attention dynamic graph convolution network model for traffic flow prediction

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Precise and reliable traffic predictions play a vital role in contemporary traffic management, particularly within complex traffic networks. Currently, the approach which utilizes static graph convolution with recurrent neural networks for traffic flow prediction fails in digging the complicated spatial and dynamic temporal correlations deeply. As a solution, we propose a dynamic graph convolution network model, aimed at enhancing traffic forecasting. Within our model, we first utilize the dynamic Laplace matrix, generated by assessing the similarity of time series changes, to facilitate graph convolution, enabling a more in-depth exploration of spatial correlations among nodes. Then, we capture local time correlations through convolutional neural networks and address long-term correlations using the self-attention mechanism. To mitigate the over-smoothing challenge related to graph fusion and deep networks, we introduce the autoregressive module to enhance the predictperformance for aperiodic sequences. Thereby, we contemplate not just the dynamic relationship between multiple time series but also the diverse facets of long-term, short-term, periodic, andnon-periodic changes inherent in time series. Experimental findings corroborate the superior performance of our proposed model compared to all benchmark models

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

Similar content being viewed by others

Availability of data and material

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

References

  1. Ali A, Zhu Y, Zakarya M (2021) Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks. Inf Sci 577:852–870. https://doi.org/10.1016/j.ins.2021.08.042

    Article  MathSciNet  Google Scholar 

  2. Ali A, Zhu Y, Zakarya M (2022) Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction. Neural Netw 145:233–247. https://doi.org/10.1016/j.neunet.2021.10.021

    Article  Google Scholar 

  3. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. ArXiv 1409. https://doi.org/10.48550/arXiv.1409.0473

  4. Bai L, Yao L, Li C, et al (2020) Adaptive graph convolutional recurrent network for traffic forecasting. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’20

  5. Chung J, Çaglar Gülehre, Cho K, et al (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. ArXiv abs/1412.3555. https://api.semanticscholar.org/CorpusID:5201925

  6. Cui Z, Henrickson KC, Ke R, et al (2018) Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting. IEEE Transactions on Intelligent Transportation Systems 21:4883–4894. https://api.semanticscholar.org/CorpusID:54434652

  7. Defferrard M, Bresson X, Vandergheynst P (2016a) Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’16, p 3844-3852

  8. Defferrard M, Bresson X, Vandergheynst P (2016b) Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’16, p 3844–3852

  9. Deng A, Hooi B (2021) Graph neural network-based anomaly detection in multivariate time series. ArXiv abs/2106.06947. https://api.semanticscholar.org/CorpusID:231646473

  10. Geng X, Li Y, Wang L, et al (2019) Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. AAAI Press, AAAI’19, https://doi.org/10.1609/aaai.v33i01.33013656

  11. Guo K, Hu Y, Qian Z et al (2022) Dynamic graph convolution network for traffic forecasting based on latent network of laplace matrix estimation. IEEE Trans Intell Transp Syst 23(2):1009–1018. https://doi.org/10.1109/TITS.2020.3019497

    Article  Google Scholar 

  12. Guo S, Lin Y, Feng N, et al (2019) Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. AAAI Press, AAAI’19, https://doi.org/10.1609/aaai.v33i01.3301922

  13. Hamed MM, Al-Masaeid HR, Said ZMB (1995) Short-term prediction of traffic volume in urban arterials. J Transp Eng 121(3):249–254. https://doi.org/10.1061/(ASCE)0733-947X(1995)121:3(249)

    Article  Google Scholar 

  14. Hamilton WL, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’17, p 1025–1035

  15. Huang R, Huang C, Liu Y, et al (2021) Lsgcn: long short-term traffic prediction with graph convolutional networks. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI’20

  16. Li M, Zhu Z (2020) Spatial-temporal fusion graph neural networks for traffic flow forecasting. ArXiv abs/2012.09641. https://api.semanticscholar.org/CorpusID:229297697

  17. Li S, Jin X, Xuan Y et al (2019) Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Curran Associates Inc., Red Hook, NY, USA

    Google Scholar 

  18. Li Y, Yu R, Shahabi C, et al (2018) Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv:1707.01926

  19. Lin Z, Feng J, Lu Z, et al (2019) Deepstn+: context-aware spatial-temporal neural network for crowd flow prediction in metropolis. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. AAAI Press, AAAI’19, https://doi.org/10.1609/aaai.v33i01.33011020

  20. Okutani I, Stephanedes YJ (1984) Dynamic prediction of traffic volume through kalman filtering theory. Transportation Research Part B: Methodological 18(1):1–11. https://doi.org/10.1016/0191-2615(84)90002-X

    Article  Google Scholar 

  21. Seo Y, Defferrard M, Vandergheynst P et al (2018) Structured sequence modeling with graph convolutional recurrent networks. In: Cheng L, Leung ACS, Ozawa S (eds) Neural Information Processing. Springer International Publishing, Cham, pp 362–373

    Chapter  Google Scholar 

  22. Su H, Zhang L, Yu S (2007) Short-term traffic flow prediction based on incremental support vector regression. In: Third International Conference on Natural Computation (ICNC 2007), pp 640–645, https://doi.org/10.1109/ICNC.2007.661

  23. Tormene P, Giorgino T, Quaglini S, et al (2009) Matching incomplete time series with dynamic time warping: an algorithm and an application to post-stroke rehabilitation. Artificial intelligence in medicine 45 1:11–34. https://api.semanticscholar.org/CorpusID:23414145

  24. Vaswani A, Shazeer NM, Parmar N, et al (2017) Attention is all you need. In: Neural Information Processing Systems, https://api.semanticscholar.org/CorpusID:13756489

  25. Wang X, Ma Y, Wang Y, et al (2020) Traffic flow prediction via spatial temporal graph neural network. In: Proceedings of The Web Conference 2020. Association for Computing Machinery, New York, NY, USA, WWW ’20, p 1082–1092, https://doi.org/10.1145/3366423.3380186

  26. Williams BM, Hoel LA (2003) Modeling and forecasting vehicular traffic flow as a seasonal arima process: Theoretical basis and empirical results. J Transp Eng 129(6):664–672. https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664)

    Article  Google Scholar 

  27. Wu CH, Ho JM, Lee D (2004) Travel-time prediction with support vector regression. IEEE Trans Intell Transp Syst 5(4):276–281. https://doi.org/10.1109/TITS.2004.837813

    Article  Google Scholar 

  28. Wu Z, Pan S, Long G, et al (2019) Graph wavenet for deep spatial-temporal graph modeling. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19. International Joint Conferences on Artificial Intelligence Organization, pp 1907–1913, https://doi.org/10.24963/ijcai.2019/264

  29. Wu Z, Pan S, Long G, et al (2020a) Connecting the dots: Multivariate time series forecasting with graph neural networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Association for Computing Machinery, New York, NY, USA, KDD ’20, p 753–763, https://doi.org/10.1145/3394486.3403118

  30. Wu Z, Pan S, Long G, et al (2020b) Connecting the dots: Multivariate time series forecasting with graph neural networks. arXiv:2005.11650

  31. Yao H, Wu F, Ke J, et al (2018) Deep multi-view spatial-temporal network for taxi demand prediction. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. AAAI Press, AAAI’18

  32. Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122

  33. Zhang J, Zheng Y, Qi D (2017) Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Press, AAAI’17, p 1655–1661

  34. Zhang J, Shi X, Xie J, et al (2018) Gaan: Gated attention networks for learning on large and spatiotemporal graphs. In: Conference on Uncertainty in Artificial Intelligence, https://api.semanticscholar.org/CorpusID:3973810

  35. Zhao L, Song Y, Zhang C et al (2020) T-gcn: A temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst 21(9):3848–3858. https://doi.org/10.1109/TITS.2019.2935152

    Article  Google Scholar 

Download references

Funding

This document is the results of the research project funded by the Natural Science Foundation of Shanghai under grant no. 20ZR1402800.

Author information

Author notes

  1. Wuneng Zhou and Wanpeng Wu have contributed equally to this work.

Authors and Affiliations

  1. College of Information Sciences and Technology, Donghua University, Shanghai, 201620, China

    Kaili Liao, Wuneng Zhou & Wanpeng Wu

Authors
  1. Kaili Liao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wuneng Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wanpeng Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Kaili Liao and Wuneng Zhou wrote the main manuscripts text. Kaili Liao prepared the experiments and figures. All authors reviewed the manusript.

Corresponding author

Correspondence to Wuneng Zhou.

Ethics declarations

Conflict of interest

The authors have no Conflict of interest to declare that are relevant to the content of this article.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liao, K., Zhou, W. & Wu, W. A self-attention dynamic graph convolution network model for traffic flow prediction. Int. J. Mach. Learn. & Cyber. (2024). https://doi.org/10.1007/s13042-024-02210-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13042-024-02210-7

Keywords

Search

Navigation