Multi-modal Representation Learning for Successive POI Recommendation

Lishan Li, Ying Liu, Jianping Wu, Lin He, Gang Ren
Proceedings of The Eleventh Asian Conference on Machine Learning, PMLR 101:441-456, 2019.

Abstract

Successive POI recommendation is a fundamental problem for location-based social networks (LBSNs). POI recommendation takes a variety of POI context information (e.g. spatial location and textual comment) and user preference into consideration. Existing POI recommendation systems mainly focus on part of the POI context and user preference with a specific modeling, which loses valuable information from other aspects. In this paper, we propose to construct a multi-modal check-in graph, a heterogeneous graph that combines five check-in aspects in a unified way. We further propose a multi-modal representation learning model based on the graph to jointly learn POI and user representations. Finally, we employ an attentional recurrent neural network based on the representations for successive POI recommendation. Experiments on a public dataset studies the effects of modeling different aspects of check-in records and demonstrates the effectiveness of the method in improving POI recommendation performance.

Cite this Paper


BibTeX
@InProceedings{pmlr-v101-li19a, title = {Multi-modal Representation Learning for Successive POI Recommendation}, author = {Li, Lishan and Liu, Ying and Wu, Jianping and He, Lin and Ren, Gang}, booktitle = {Proceedings of The Eleventh Asian Conference on Machine Learning}, pages = {441--456}, year = {2019}, editor = {Lee, Wee Sun and Suzuki, Taiji}, volume = {101}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v101/li19a/li19a.pdf}, url = {https://proceedings.mlr.press/v101/li19a.html}, abstract = {Successive POI recommendation is a fundamental problem for location-based social networks (LBSNs). POI recommendation takes a variety of POI context information (e.g. spatial location and textual comment) and user preference into consideration. Existing POI recommendation systems mainly focus on part of the POI context and user preference with a specific modeling, which loses valuable information from other aspects. In this paper, we propose to construct a multi-modal check-in graph, a heterogeneous graph that combines five check-in aspects in a unified way. We further propose a multi-modal representation learning model based on the graph to jointly learn POI and user representations. Finally, we employ an attentional recurrent neural network based on the representations for successive POI recommendation. Experiments on a public dataset studies the effects of modeling different aspects of check-in records and demonstrates the effectiveness of the method in improving POI recommendation performance.} }
Endnote
%0 Conference Paper %T Multi-modal Representation Learning for Successive POI Recommendation %A Lishan Li %A Ying Liu %A Jianping Wu %A Lin He %A Gang Ren %B Proceedings of The Eleventh Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Wee Sun Lee %E Taiji Suzuki %F pmlr-v101-li19a %I PMLR %P 441--456 %U https://proceedings.mlr.press/v101/li19a.html %V 101 %X Successive POI recommendation is a fundamental problem for location-based social networks (LBSNs). POI recommendation takes a variety of POI context information (e.g. spatial location and textual comment) and user preference into consideration. Existing POI recommendation systems mainly focus on part of the POI context and user preference with a specific modeling, which loses valuable information from other aspects. In this paper, we propose to construct a multi-modal check-in graph, a heterogeneous graph that combines five check-in aspects in a unified way. We further propose a multi-modal representation learning model based on the graph to jointly learn POI and user representations. Finally, we employ an attentional recurrent neural network based on the representations for successive POI recommendation. Experiments on a public dataset studies the effects of modeling different aspects of check-in records and demonstrates the effectiveness of the method in improving POI recommendation performance.
APA
Li, L., Liu, Y., Wu, J., He, L. & Ren, G.. (2019). Multi-modal Representation Learning for Successive POI Recommendation. Proceedings of The Eleventh Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 101:441-456 Available from https://proceedings.mlr.press/v101/li19a.html.

Related Material