Abstract
With the rapid development of location-based social networks (LBSNs), point of interests (POI) recommendation has become an important means to help people discover attractive and interesting locations from billions of locations globally. However, this recommendation is very challenging compared to the traditional recommender systems. A user may visit only a limited number of POIs, leading to a very sparse user-item matrix. This matrix becomes even sparser when the user travels to a distant place as most of the items visited by a user are usually located within a short distance from the user’s home. Moreover, user interests and behavior patterns may vary dramatically across different time and different geographical regions. On the other hand, in reality, human movement exhibits sequential patterns. Thus, how to predict users’ next move based on her previous visited locations is important and challenging in LBSNs. Our project focuses on offering a more accurate and efficient recommender system by overcoming the aforementioned challenges, and it contains the following three parts:In the first part, we design ST-SAGE, a spatial-temporal sparse additive generative model for POI recommendation. ST-SAGE considers both personal interests of the users and the preferences of the crowd in the target region at the given time by exploiting both the co-occurrence patterns of POIs and the content of POIs. To further alleviate the data sparsity issue, ST-SAGE exploits the geographical correlation by smoothing the crowd’s preferences over a well-designed spatial index structure called spatial pyramid. To speed up the training process of ST-SAGE, we implement a parallel version of the model inference algorithm on the GraphLab framework.The second part aims to leveraging sequential patterns in POI recommendation. However, this is very challenging, considering 1) users’ check-in data in LBSNs has a low sampling rate in both space and time, which renders existing location prediction techniques on GPS trajectories ineffective; 2) the prediction space is extremely large, with millions of distinct locations as the next prediction target, which impedes the application of classical Markov chain models; and 3) there is no existing framework that unifies users’ personal interests and the sequential influence of recently visited locations in a principled manner. In light of the above challenges, we propose a sequential personalized POI recommendation framework (SPORE) which introduces a novel latent variable topic-region to model and fuse sequential influence with personal interests in the latent and exponential space. The advantages of modeling the sequential effect at the topic-region level include a significantly reduced prediction space, an effective alleviation of data sparsity and a direct expression of the semantic meaning of users’ spatial activities.In the third part, we focus on speeding up the online top-k recommendation process. In this part, we design two methods. The first method is able to extract the exact top-k results. It is a scalable query processing technique for top-k recommendation developed by extending the threshold algorithm (TA), which accesses items from the K sorted lists at location l on time t and computes the top-k results by scanning the minimum number of POIs. The second method, which is called as asymmetric Locality Sensitive Hashing (ALSH) technique, approximates the top-k results with less time. It speeds up the online top-k recommendation process by extending the traditional LSH to Maximum Inner-Product Search (MIPS).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.