Joint Modeling of Multimodal Information Based on Dynamic and Static Knowledge Graphs for Next POI Recommendation

As one of the location-based social network (LBSN) applications, next point-of-interest (POI) recommendation is devoted to predicting a user’s next interested locations based on check-in trajectories, which has received a lot of attention. In recent research endeavors, graph neural network (GNN) has demonstrated exceptional performance by incorporating global user/POI features into the learning framework. Nevertheless, most existing approaches merely target on one or two factors present in trajectories, such as geographic location, social networks, or user reviews, failing to fully exploit the multimodal information in real-world scenarios. Additionally, user’s behavior patterns embedded in historical trajectories have not been effectively partitioned, posing challenges to the learning of user’s evolving preferences over time. To this end, this study proposes multimodal intertwined network (MINet), a novel model based on dynamic and static knowledge graphs, to tackle the challenges of multimodality in the next POI recommendation. On the one hand, temporal dynamic knowledge graph is established to learn the evolution of user preferences by capturing behavior patterns at various time slices. On the other hand, a grouping static knowledge graph is constructed to learn the stable user/POI features through aggregating multimodal relations. Furthermore, to achieve enhanced information fusion, this study learns the features of POIs and users from the two types of knowledge graphs, respectively. Experiments on three real-world datasets demonstrated that MINet outperforms the state-of-the-art methods.