Abstract
Point-of-interest (POI) recommendation helps users filter information and discover their interests. In recent years, graph convolution network (GCN)–based methods have become state-of-the-art algorithms for improving recommendation performance. Especially integrating GCN with multiple information, such as geographical information, is a promising way to achieve better performance; however, it tends to increase the number of trainable parameters, resulting in the difficulty of model training to reduce the performance. In this study, we mine users’ active areas and extend the definition of neighbors in GCN, called active area neighbors. Our study is the first attempt to integrate geographic information into a GCN POI recommendation system without increasing the number of trainable parameters and maintaining the ease of training. The experimental evaluation confirms that compared with the state-of-the-art lightweight GCN models, our method improves \(Recall@10\) from 0.0562 to 0.0590 (4.98%) on Yelp dataset and from 0.0865 to 0.0898 (3.82%) on Gowalla dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Baral, R., Li, T.: Maps: A multi aspect personalized poi recommender system. In: Proceedings of the 10th ACM RecSys, pp. 281–284 (2016)
Chang, B., Jang, G., Kim, S., Kang, J.: Learning graph-based geographical latent representation for point-of-interest recommendation. In: Proceedings of the 29th ACM CIKM, pp. 135–144 (2020)
Chen, L., Wu, L., Hong, R., Zhang, K., Wang, M.: Revisiting graph based collaborative filtering: a linear residual graph convolutional network approach. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 27–34 (2020)
Elmi, S., Benouaret, K., Tan, K.L. Social and spatio-temporal learning for contextualized next points-of-interest prediction. In: Proceedings of 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence, pp.322–329 (2021)
Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the 2nd ACM SIGKDD, pp. 226–231 (1996)
Fan, W., et al.: Graph neural networks for social recommendation. In: Proceedings of the WWW, pp. 417–426 (2019)
Ference, G., Ye, M., Lee, W.C.: Location recommendation for out-of-town users in location-based social networks. In: Proceedings of the 22nd ACM CIKM, pp. 721–726 (2013)
Han, P., Shang, S., Sun, A., Zhao, P., Zheng, K., Zhang, X.: Point-of-interest recommendation with global and local context. IEEE Trans. Knowl. Data Eng. (2021). https://doi.org/10.1109/TKDE.2021.3059744
He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: LightGCN: simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd ACM SIGIR, pp. 639–648 (2020)
Li, X., Cong, G., Li, X., Pham, T., Krishnaswamy, S.: Rank-GeoFM: a ranking based geographical factorization method for point of interest recommendation. In: Proceedings of the 38th ACM SIGIR, pp. 433–442 (2015)
Liu, W., Wang, Z.J., Yao, B., Yin, J.: Geo-ALM: POI recommendation by fusing geographical information and adversarial learning mechanism. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 1807–1813 (2019)
Liu, Y., Pham, T.A.N., Cong, G., Yuan, Q.: An experimental evaluation of point-of-interest recommendation in location-based social networks. Proc. VLDB Endow. 10(10), 1010–1021 (2017)
Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: BPR: Bayesian personalized ranking from implicit feedback. In: arXiv preprint arXiv:1205.2618 (2012)
Wang, X., He, X., Wang, M., Feng, F., Chua, T.: Neural graph collaborative filtering. In: Proceedings of the 42nd ACM SIGIR, pp. 165–174 (2019)
Ye, M., Yin, P., Lee, W.C., Lee, D.: Exploiting geographical influence for collaborative point-of-interest recommendation. In: Proceedings of the 34th ACM SIGIR, pp. 325–334 (2011)
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W., Leskovec, J.: Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD, pp. 974–983 (2018)
Zhang, J., Chow, C.: GeoSoCa: exploiting geographical, social and categorical correlations for point-of-interest recommendations. In: Proceedings of the 38th SIGIR, pp. 443–452 (2015)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mo, F., Yamana, H. (2022). GN-GCN: Combining Geographical Neighbor Concept with Graph Convolution Network for POI Recommendation. In: Pardede, E., Delir Haghighi, P., Khalil, I., Kotsis, G. (eds) Information Integration and Web Intelligence. iiWAS 2022. Lecture Notes in Computer Science, vol 13635. Springer, Cham. https://doi.org/10.1007/978-3-031-21047-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-21047-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21046-4
Online ISBN: 978-3-031-21047-1
eBook Packages: Computer ScienceComputer Science (R0)