An aentive interaction network for context-aware recommendations

Context-aware Recommender Systems (CARS) have attracted a lot of attention recently because of the impact of contextual information on user behaviors. Recent state-of-the-art methods represent the relations between users/items and contexts as a tensor, with which it is dicult to distinguish the impacts of dierent contextual factors and to model complex, non-linear interactions between contexts and users/items. In this paper, we propose a novel neural model, named Attentive Interaction Network (AIN), to enhance CARS through adaptively capturing the interactions between contexts and users/items. Specifically, AIN contains an Interaction-Centric Module to capture the interaction eects of contexts on users/items; a User-Centric Module and an Item-Centric Module to model respectively how the interaction eects inuence the user and item representations. The user and item representations under interaction eects are combined to predict the recommendation scores. We further employ eect-level attention mechanism to aggregate multiple interaction eects. Extensive experiments on two rating datasets and one ranking dataset show that the proposed AIN outperforms state-of-the-art CARS methods. In addition, we also nd that AIN provides recommendations with better explanation ability with respect to contexts than the existing approaches.