Point-of-Interest (POI) recommendation is one of the most important location-based services helping people discover interesting venues or services. However, the extreme user-POI matrix sparsity and the vary- ing spatio-temporal context pose challenges for POI systems, which af- fects the quality of POI recommendations. To this end, we propose a translation-based relation embedding for POI recommendation. Our ap- proach encodes the temporal and geographic information, as well as se- mantic contents e ectively in a low-dimensional relation space by using Knowledge Graph Embedding techniques. To further alleviate the issue of user-POI matrix sparsity, a combined matrix factorization framework is built on a user-POI graph to enhance the inference of dynamic per- sonal interests by exploiting the side-information. Experiments on two real-world datasets demonstrate the e ectiveness of our proposed model.
@inproceedings{DBLP:conf/pakdd/WangSRK20,
author = {Xianjing Wang and
Flora D. Salim and
Yongli Ren and
Piotr Koniusz},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/conf/pakdd/WangSRK20.bib},
booktitle = {Advances in Knowledge Discovery and Data Mining - 24th Pacific-Asia
Conference, PAKDD 2020, Singapore, May 11-14, 2020, Proceedings,
Part I},
doi = {10.1007/978-3-030-47426-3_5},
editor = {Hady W. Lauw and
Raymond Chi-Wing Wong and
Alexandros Ntoulas and
Ee-Peng Lim and
See-Kiong Ng and
Sinno Jialin Pan},
pages = {53--64},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
timestamp = {Fri, 22 May 2020 01:00:00 +0200},
title = {Relation Embedding for Personalised Translation-Based POI Recommendation},
url = {https://doi.org/10.1007/978-3-030-47426-3_5},
volume = {12084},
year = {2020}
}
© 2021 Flora Salim - CRUISE Research Group.