TY - GEN
T1 - Learning Graph-Based Geographical Latent Representation for Point-of-Interest Recommendation
AU - Chang, Buru
AU - Jang, Gwanghoon
AU - Kim, Seoyoon
AU - Kang, Jaewoo
N1 - Funding Information:
This research was supported by the National Research Foundation of Korea (No. NRF-2017R1A2A1A17069645, NRF-2017M3C4A7065887).
Publisher Copyright:
© 2020 ACM.
PY - 2020/10/19
Y1 - 2020/10/19
N2 - Several geographical latent representation models that capture geographical influences among points-of-interest (POIs) have been proposed. Although the models improve POI recommendation performance, they depend on shallow methods that cannot effectively capture highly non-linear geographical influences from complex user-POI networks. In this paper, we propose a new graph-based geographical latent representation model (GGLR) which can capture highly non-linear geographical influences from complex user-POI networks. Our proposed GGLR considers two types of geographical influences: ingoing influences and outgoing influences. Based on a graph auto-encoder, geographical latent representations of ingoing and outgoing influences are trained to increase geographical influences between two consecutive POIs that frequently appear in check-in histories. Furthermore, we propose a graph neural network-based POI recommendation model (GPR) that uses the trained geographical latent representations of ingoing and outgoing influences for the estimation of user preferences. In the experimental evaluation on real-world datasets, we show that GGLR effectively captures highly non-linear geographical influences and GPR achieves state-of-the-art performance.
AB - Several geographical latent representation models that capture geographical influences among points-of-interest (POIs) have been proposed. Although the models improve POI recommendation performance, they depend on shallow methods that cannot effectively capture highly non-linear geographical influences from complex user-POI networks. In this paper, we propose a new graph-based geographical latent representation model (GGLR) which can capture highly non-linear geographical influences from complex user-POI networks. Our proposed GGLR considers two types of geographical influences: ingoing influences and outgoing influences. Based on a graph auto-encoder, geographical latent representations of ingoing and outgoing influences are trained to increase geographical influences between two consecutive POIs that frequently appear in check-in histories. Furthermore, we propose a graph neural network-based POI recommendation model (GPR) that uses the trained geographical latent representations of ingoing and outgoing influences for the estimation of user preferences. In the experimental evaluation on real-world datasets, we show that GGLR effectively captures highly non-linear geographical influences and GPR achieves state-of-the-art performance.
KW - POI recommendation
KW - collaborative filtering
KW - location-based social network
KW - point-of-interest
KW - recommender system
UR - http://www.scopus.com/inward/record.url?scp=85095862971&partnerID=8YFLogxK
U2 - 10.1145/3340531.3411905
DO - 10.1145/3340531.3411905
M3 - Conference contribution
AN - SCOPUS:85095862971
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 135
EP - 144
BT - CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 29th ACM International Conference on Information and Knowledge Management, CIKM 2020
Y2 - 19 October 2020 through 23 October 2020
ER -