Modeling Spatio-temporal Neighbourhood for Personalized Point-of-interest Recommendation

Modeling Spatio-temporal Neighbourhood for Personalized Point-of-interest Recommendation

Xiaolin Wang, Guohao Sun, Xiu Fang, Jian Yang, Shoujin Wang

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 3530-3536. https://doi.org/10.24963/ijcai.2022/490

Point-of-interest (POI) recommendations can help users explore attractive locations, which is playing an important role in location-based social networks (LBSNs). In POI recommendations, the results are largely impacted by users' preferences. However, the existing POI methods model user and location almost separately, which cannot capture users' personal and dynamic preferences to location. In addition, they also ignore users' acceptance to distance/time of location. To overcome the limitations of the existing methods, we first introduce Knowledge Graph with temporal information (known as TKG) into POI recommendation, including both user and location with timestamps. Then, based on TKG, we propose a Spatial-Temporal Graph Convolutional Attention Network (STGCAN), a novel network that learns users' preferences on TKG by dynamically capturing the spatial-temporal neighbourhoods. Specifically, in STGCAN, we construct receptive fields on TKG to aggregate neighbourhoods of user and location respectively at each timestamp. And we measure the spatial-temporal interval as users' acceptance to distance/time with self-attention. Experiments on three real-world datasets demonstrate that the proposed model outperforms the state-of-the-art POI recommendation approaches.
Keywords:
Machine Learning: Recommender Systems
Data Mining: Knowledge Graphs and Knowledge Base Completion