%0 Conference Paper %1 Xie:2016:LGP:2983323.2983711 %A Xie, Min %A Yin, Hongzhi %A Wang, Hao %A Xu, Fanjiang %A Chen, Weitong %A Wang, Sen %B Proceedings of the 25th ACM International on Conference on Information and Knowledge Management %C New York, NY, USA %D 2016 %I ACM %K POI-embedding location-based-recommendation social-information-access %P 15--24 %R 10.1145/2983323.2983711 %T Learning Graph-based POI Embedding for Location-based Recommendation %U http://doi.acm.org/10.1145/2983323.2983711 %X With the rapid prevalence of smart mobile devices and the dramatic proliferation of location-based social networks (LBSNs), location-based recommendation has become an important means to help people discover attractive and interesting points of interest (POIs). However, the extreme sparsity of user-POI matrix and cold-start issue create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Moreover, location-based recommendation requires spatiotemporal context awareness and dynamic tracking of the user's latest preferences in a real-time manner. To address these challenges, we stand on recent advances in embedding learning techniques and propose a generic graph-based embedding model, called GE, in this paper. GE jointly captures the sequential effect, geographical influence, temporal cyclic effect and semantic effect in a unified way by embedding the four corresponding relational graphs (POI-POI, POI-Region, POI-Time and POI-Word)into a shared low dimensional space. Then, to support the real-time recommendation, we develop a novel time-decay method to dynamically compute the user's latest preferences based on the embedding of his/her checked-in POIs learnt in the latent space. We conduct extensive experiments to evaluate the performance of our model on two real large-scale datasets, and the experimental results show its superiority over other competitors, especially in recommending cold-start POIs. Besides, we study the contribution of each factor to improve location-based recommendation and find that both sequential effect and temporal cyclic effect play more important roles than geographical influence and semantic effect. %@ 978-1-4503-4073-1

@inproceedings{Xie:2016:LGP:2983323.2983711, abstract = {With the rapid prevalence of smart mobile devices and the dramatic proliferation of location-based social networks (LBSNs), location-based recommendation has become an important means to help people discover attractive and interesting points of interest (POIs). However, the extreme sparsity of user-POI matrix and cold-start issue create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Moreover, location-based recommendation requires spatiotemporal context awareness and dynamic tracking of the user's latest preferences in a real-time manner. To address these challenges, we stand on recent advances in embedding learning techniques and propose a generic graph-based embedding model, called GE, in this paper. GE jointly captures the sequential effect, geographical influence, temporal cyclic effect and semantic effect in a unified way by embedding the four corresponding relational graphs (POI-POI, POI-Region, POI-Time and POI-Word)into a shared low dimensional space. Then, to support the real-time recommendation, we develop a novel time-decay method to dynamically compute the user's latest preferences based on the embedding of his/her checked-in POIs learnt in the latent space. We conduct extensive experiments to evaluate the performance of our model on two real large-scale datasets, and the experimental results show its superiority over other competitors, especially in recommending cold-start POIs. Besides, we study the contribution of each factor to improve location-based recommendation and find that both sequential effect and temporal cyclic effect play more important roles than geographical influence and semantic effect.}, acmid = {2983711}, added-at = {2017-02-08T21:22:31.000+0100}, address = {New York, NY, USA}, author = {Xie, Min and Yin, Hongzhi and Wang, Hao and Xu, Fanjiang and Chen, Weitong and Wang, Sen}, biburl = {https://www.bibsonomy.org/bibtex/2111b2b816bc745890b5fb86495a20488/xianteng}, booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management}, description = {Learning Graph-based POI Embedding for Location-based Recommendation}, doi = {10.1145/2983323.2983711}, interhash = {fa1448c2779915e64a797334d56be712}, intrahash = {111b2b816bc745890b5fb86495a20488}, isbn = {978-1-4503-4073-1}, keywords = {POI-embedding location-based-recommendation social-information-access}, location = {Indianapolis, Indiana, USA}, numpages = {10}, pages = {15--24}, publisher = {ACM}, series = {CIKM '16}, timestamp = {2017-02-08T21:22:31.000+0100}, title = {Learning Graph-based POI Embedding for Location-based Recommendation}, url = {http://doi.acm.org/10.1145/2983323.2983711}, year = 2016 }