Abstract
Next Point-of-Interest (POI) recommendation has become a vital research trend, helping people find interesting and attractive locations. Existing methods usually exploit the individual-level POI sequences but failed to utilize the information of collective-level POI sequences. Since collective-level POIs, like shopping malls or plazas, are common in the real world, we argue that only the individual-level POI sequences cannot represent more semantic features and cannot express complete transition patterns. To this end, we propose a novel Multi-Granularity Self-Attention Network (MGSAN) for next POI recommendation, which utilizes the multi-granularity representation and the self-attention mechanism to capture the transition patterns of individual-level and collective-level POI sequences on two different levels of granularities. Specifically, individual-level and collective-level POI sequences are first constructed and embeddings of each check-in tuple are normalized. Then, MGSAN incorporates spatio-temporal features by introducing two temporal-aware encoders and two spatial-aware encoders and learns sequential patterns with the self-attention network for two granularities. Finally, we recommended a user’s next POI with the help of two sub-tasks, i.e., the activity task to predict the next category and the auxiliary task to predict the next POI type. Extensive experiments on three real-world datasets show that MGSAN outperforms state-of-the-art methods consistently.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, Z., et al.: Co-attentive multi-task learning for explainable recommendation. In: IJCAI, pp. 2137–2143 (2019)
Feng, S., Li, X., Zeng, Y., Cong, G., Chee, Y.M., Yuan, Q.: Personalized ranking metric embedding for next new POI recommendation. In: IJCAI, pp. 2069–2075 (2015)
Girshick, R.B.: Fast R-CNN. In: ICCV, pp. 1440–1448 (2015)
He, J., Li, X., Liao, L.: Category-aware next point-of-interest recommendation via listwise Bayesian personalized ranking. In: IJCAI, pp. 1837–1843 (2017)
Huang, L., Ma, Y., Wang, S., Liu, Y.: An attention-based spatiotemporal LSTM network for next poi recommendation. IEEE Trans. Serv. Comput. (2019). https://doi.org/10.1109/TSC.2019.2918310
Huang, X., Qian, S., Fang, Q., Sang, J., Xu, C.: CSAN: contextual self-attention network for user sequential recommendation. In: ACM Multimedia, pp. 447–455 (2018)
Kang, W., McAuley, J.J.: Self-attentive sequential recommendation. In: ICDM, pp. 197–206 (2018)
Li, X., Cong, G., Li, X., Pham, T.N., Krishnaswamy, S.: Rank-GeoFM: a ranking based geographical factorization method for point of interest recommendation. In: SIGIR, pp. 433–442 (2015)
Lian, D., Zhao, C., Xie, X., Sun, G., Chen, E., Rui, Y.: GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation. In: KDD, pp. 831–840 (2014)
Liao, D., Liu, W., Zhong, Y., Li, J., Wang, G.: Predicting activity and location with multi-task context aware recurrent neural network. In: IJCAI, pp. 3435–3441 (2018)
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)
Liu, X., Liu, Y., Aberer, K., Miao, C.: Personalized point-of-interest recommendation by mining users’ preference transition. In: CIKM, pp. 733–738 (2013)
Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: BPR: Bayesian personalized ranking from implicit feedback. In: UAI, pp. 452–461 (2009)
Tang, Z., Fishwick, P.A.: Feedforward neural nets as models for time series forecasting. INFORMS J. Comput. 5(4), 374–385 (2017)
Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)
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)
Zhang, L., et al.: An interactive multi-task learning framework for next POI recommendation with uncertain check-ins. In: IJCAI, pp. 3551–3557 (2020)
Zhao, P., et al.: Where to go next: a spatio-temporal gated network for next POI recommendation. In: AAAI, pp. 5877–5884 (2019)
Zhao, S., Zhao, T., King, I., Lyu, M.R.: Geo-teaser: geo-temporal sequential embedding rank for point-of-interest recommendation. In: WWW, pp. 153–162 (2017)
Acknowledgements
This research was partially supported by NSFC (No. 61876117, 61876217, 61872258, 61728205), Open Program of Key Lab of IIP of CAS (No. IIP2019-1) and the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Y., Xian, X., Zhao, P., Liu, Y., Sheng, V.S. (2021). MGSAN: A Multi-granularity Self-attention Network for Next POI Recommendation. In: Zhang, W., Zou, L., Maamar, Z., Chen, L. (eds) Web Information Systems Engineering – WISE 2021. WISE 2021. Lecture Notes in Computer Science(), vol 13081. Springer, Cham. https://doi.org/10.1007/978-3-030-91560-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-91560-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91559-9
Online ISBN: 978-3-030-91560-5
eBook Packages: Computer ScienceComputer Science (R0)