Skip to main content
SpringerLink
Log in

GCMT: a graph-contextualized multitask spatio-temporal joint prediction model for cellular trajectories

  • Published:
World Wide Web Aims and scope Submit manuscript

Abstract

Spatio-temporal joint prediction aims to simultaneously predict the next location and the corresponding switch time for a cellular trajectory. An accuracy prediction requires not only sequential information but also spatio-temporal context information. Although existing methods can utilize trajectory modeling to support the joint prediction, they fail to learn the complicated geographical influence, temporal dependencies and various context information. To this end, we propose a graph-contextualized multitask learning method for spatio-temporal joint prediction. Specially, to model each location’s spatio-temporal dependencies, a graph embedding module is adopted to jointly capture the geographical influence and temporal cyclic effect by embedding three relational graphs (i.e., location-location, location-region, and location-time) into a shared low dimensional space. Moreover, considering the impact of traffic-related contexts on trajectory movement, we design a traffic encoder to model the dynamic of traffic flows, which comprises several spatio-temporal blocks combining temporal gated CNN with spatial graph convolution. In addition, a context-attention layer is proposed to fuse trajectory sequential information and traffic information based on various background factors. Finally, GCMT is evaluated on two real-world datasets to demonstrate its advantages.

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

Similar content being viewed by others

References

  1. Blondel, V. D., Decuyper, A., Krings, G.: A survey of results on mobile phone datasets analysis. EPJ Data Sci. 4(1), 10 (2015)

    Article  Google Scholar 

  2. Chen, L., Shang, S., Feng, S., Kalnis, P.: Parallel subtrajectory alignment over massive-scale trajectory data. In: IJCAI, pp 3613–3619 (2021)

  3. 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 (2019)

  4. 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)

    Article  Google Scholar 

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

  6. Kong, D, Wu, F: HST-LSTM: A hierarchical spatial-temporal long-short term memory network for location prediction. In: IJCAI, pp 2341–2347 (2018)

  7. Liu, Q., Wu, S., Wang, L., Tan, T.: Predicting the next location: A recurrent model with spatial and temporal contexts. In: AAAI, pp 194–200 (2016)

  8. Yang, G., Cai, Y., Reddy, C. K.: Spatio-temporal check-in time prediction with recurrent neural network based survival analysis. In: IJCAI, pp. 2976–2983 (2018)

  9. Aalen, O., Borgan, O., Gjessing, H.: Survival and event history analysis: a process point of view. Springer Science & Business Media (2008)

  10. Du, N., Dai, H., Trivedi, R., Upadhyay, U., Gomez-rodriguez, M., Song, L.: Recurrent marked temporal point processes: Embedding event history to vector. In: SIGKDD, pp 1555–1564 (2016)

  11. Xiao, S, Yan, J., Yang, X., Zha, H., Chu, S. M.: Modeling the intensity function of point process via recurrent neural networks. In: AAAI, pp. 1597–1603 (2017)

  12. Xu, Y., Xu, J., Fang, J., Liu, A., Zhao, L.: When multitask learning make a difference: Spatio-temporal joint prediction for cellular trajectories. In: DASFAA, ser, LNCS, vol. 13245, pp 207–223 (2022)

  13. Zheng, K., Shang, S., Yuan, N. J., Yang, Y. : Towards efficient search for activity trajectories. In: ICDE, pp 230–241 (2013)

  14. Shang, S., Chen, L., Jensen, C. S., Wen, J., Kalnis, P.: Searching trajectories by regions of interest. TKDE 29(7), 1549–1562 (2017)

    Google Scholar 

  15. Shang, S., Chen, L., Wei, Z., Jensen, C. S., Zheng, K., Kalnis, P.: Parallel trajectory similarity joins in spatial networks. VLDB J. 27(3), 395–420 (2018)

    Article  Google Scholar 

  16. Shang, S., Chen, L., Zheng, K., Jensen, C. S., Wei, Z., Kalnis, P.: Parallel trajectory-to-location join. TKDE 31(6), 1194–1207 (2019)

    Google Scholar 

  17. Yang, C., Chen, L., Wang, H., Shang, S.: Towards efficient selection of activity trajectories based on diversity and coverage. In: AAAI, pp 689–696 (2021)

  18. Han, P., Wang, J., Yao, D., Shang, S., Zhang, X.: A graph-based approach for trajectory similarity computation in spatial networks. In: KDD, pp 556–564 (2021)

  19. Sun, H., Xu, J., Zheng, K., Zhao, P., Chao, P., Zhou, X.: MFNP: A meta-optimized model for few-shot next POI recommendation. In: IJCAI, pp 3017–3023 (2021)

  20. Xu, J., Zhao, J., Zhou, R., Liu, C., Zhao, P., Zhao, L.: Predicting destinations by a deep learning based approach. TKDE 33(2), 651–666 (2021)

    Google Scholar 

  21. Sun, H., Xu, J., Zhou, R., Chen, W., Zhao, L., Liu, C.: HOPE: A hybrid deep neural model for out-of-town next POI recommendation. WWW 24 (5), 1749–1768 (2021)

    Google Scholar 

  22. Xu, S., Zhang, R., Cheng, W., Xu, J.: Mtlm: a multi-task learning model for travel time estimation. GeoInformatica, no. 1 (2020)

  23. Yang, G., Cai, Y., Reddy, C. K. : Recurrent spatio-temporal point process for check-in time prediction. In: CIKM, pp 2203–2211 (2018)

  24. Yang, D., Fankhauser, B., Rosso, P., Cudré-Mauroux, P.: Location prediction over sparse user mobility traces using rnns: Flashback in hidden states. In: IJCAI, pp 2184–2190 (2020)

  25. Zhang, Y., Yang, Q.: A survey on multi-task learning. CoRR, 1707.08114 (2017)

  26. Fang, Y., Ma, Z., Zhang, Z., Zhang, X., Bai, X: Dynamic multi-task learning with convolutional neural network. In: IJCAI, pp 1668–1674 (2017)

  27. Liang, W., Zhang, W.: Learning social relations and spatiotemporal trajectories for next check-in inference, TNNLS (2020)

  28. Chen, Y., Long, C., Cong, G., Li, C.: Context-aware deep model for joint mobility and time prediction. In: WSDM, pp 106–114 (2020)

  29. Xue, A. Y., Zhang, R., Zheng, Y., Xie, X., Huang, J., Xu, Z.: Destination prediction by sub-trajectory synthesis and privacy protection against such prediction. In: ICDE, pp 254–265 (2013)

  30. Zhao, J., Xu, J., Zhou, R., Zhao, P., Liu, C., Zhu, F.: On prediction of user destination by sub-trajectory understanding: A deep learning based approach. In: CIKM, ACM, pp. 1413–1422 (2018)

  31. Xie, M., Yin, H., Wang, H., Xu, F., Chen, W., Wang, S.: Learning graph-based POI embedding for location-based recommendation. In: CIKM, pp 15–24 (2016)

  32. Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS, pp 3111–3119 (2013)

  33. Recht, B., Ré, C., Wright, S. J., Niu, F.: Hogwild: A lock-free approach to parallelizing stochastic gradient descent. In: NIPS, pp 693–701 (2011)

  34. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: NIPS, pp 5998–6008 (2017)

  35. 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(3), 14:1-14:22 (2022)

    Google Scholar 

  36. Dauphin, Y. N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. In: ICML, vol. 70, pp 933–941 (2017)

  37. Kipf, T. N., Welling, M.: “Semi-supervised classification with graph convolutional networks. In: ICLR (2017)

  38. Seiler, M. C., Seiler, F. A., et al.: Numerical recipes in c: the art of scientific computing. Risk Anal. 9(3), 415–416 (1989)

    Article  Google Scholar 

  39. Zuo, S., Jiang, H., Li, Z., Zhao, T., Zha, H.: Transformer hawkes process. In: ICML, vol. 119, pp 11692–11702 (2020)

Download references

Acknowledgements

This work is supported by National Natural Science Foundation of China (No. 61872166), Six Talent Peaks Project of Jiangsu Province (2019 XYDXX-161).

Funding

The funding concludes the National Natural Science Foundation of China (No. 61872166), Six Talent Peaks Project of Jiangsu Province (2019 XYDXX-161).

Author information

Authors and Affiliations

  1. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China

    Yu Sang & Zhenping Xie

  2. School of Computer Science and Technology, Soochow University, Suzhou, China

    Yuan Xu

  3. Dalian Maritime University, Dalian, China

    Bo Ning

Authors
  1. Yu Sang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuan Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bo Ning
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhenping Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Yu Sang and Yuan Xu wrote the main manuscript text. Bo Ning and Zhenping Xie participated in model design and technical discussion.

Corresponding author

Correspondence to Bo Ning.

Ethics declarations

Competing interests

We declare that we have no conflict of interest.

Additional information

Availability of supporting data

Hangzhou and Xiamen datasets are non-public datasets.

Publisher’s note

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

Yu Sang and Yuan Xu contributed equally to this work.

This article belongs to the Topical Collection: Special Issue on Spatiotemporal Data Management and Analytics for Recommenders Guest Editors: Shuo Shang, Xiangliang Zhang and Panos Kalnis

Rights and permissions

Springer Nature or its licensor 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

Sang, Y., Xu, Y., Ning, B. et al. GCMT: a graph-contextualized multitask spatio-temporal joint prediction model for cellular trajectories. World Wide Web 26, 1649–1665 (2023). https://doi.org/10.1007/s11280-022-01095-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11280-022-01095-2

Keywords

Search

Navigation