Position and Distance: Recommendation beyond Matrix Factorization

For the last two decades, matrix factorization has become one of the fundamental methods for tackling recommendation problems. Recent studies demonstrate that the interaction function dot product used in MF can limit its expressiveness and lead to sub-optimal solutions. In this work, we propose modelling user-item interaction paŠerns in an alternative way by considering positions and distances of users and items. We assume that users and items can be positioned in a low dimensional space and their explicit closeness can be measured using Euclidean distance metric. In addition, we adopted a weighted strategy to adaptively assign different con€dence levels for positive and negative samples, which introduces more ƒexibility for recommendation with implicit interactions. Comprehensive experiments on multiple real-world datasets demonstrate superior performances of our model over state-of-the-art competing methods including conventional matrix factorization based approaches and recent metric learning based approaches.