Graph Attentive Network for Region Recommendation with POI- and ROI-Level Attention

Abstract

Due to the prevalence of human activity in urban space, recommending ROIs (region-of-interest) to users becomes an important task in social networks. The fundamental problem is how to aggregate users’ preferences over POIs (point-of-interest) to infer the users’ region-level mobility patterns. We emphasize two facts in this paper: (1) there simultaneously exists ROI-level and POI-level implicitness that blurs the users’ underlying preferences; and (2) individual POIs should have non-uniform weights and more importantly, the weights should vary across different users. To address these issues, we contribute a novel solution, namely GANR$^2$ (Graph Attentive Neural Network for Region Recommendation), based on the recent development of attention network and Neural Graph Collaborative Filtering (NGCF). Specifically, to learn the user preferences over ROIs, we provide a principled neural network model equipped with two attention modules: the POI-level attention module, to select informative POIs of one ROI, and the ROI-level attention module, to learn the ROI preferences. Moreover, we learn the interactions between users and ROIs under the NGCF framework. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework.