A Hierarchical Attention Model for Social Contextual Image Recommendation
Image based social networks are among the most popular social networking services in recent years. With tremendous images uploaded everyday, understanding users' preferences to the user-generated images and making recommendations have become an urgent need. In fact, many hybrid models have been proposed to fuse various kinds of side information for enhancing recommendation performance. Nevertheless, these previous works failed to capture the unique characteristics of social image platforms or relied on predefined weights in combining different kinds of information. To this end, in this paper, we develop a hierarchical attention model for social contextual image recommendation. In addition to basic latent user interest modeling in the popular matrix factorization based recommendation, we identify three key aspects (i.e., upload coherence, social influence, and owner admiration) that affect each user's latent preferences, where each aspect summarizes a contextual factor from the complex relationships between users and images. After that, we design a hierarchical attention network that naturally mirrors the hierarchical relationship (elements in each aspects level, and the aspect level) of users' latent interests with the identified key aspects. Finally, extensive experimental results on real-world datasets clearly show the superiority of our proposed model.