A recommender system generates personalized recommendations for a user by computing the preference score of items, sorting the items according to the score, and filtering the top-Kitemswith high scores. While sorting and ranking items are integral for this recommendation procedure,it is nontrivial to incorporate them in the process of end-to-end model training since sorting is non-differentiable and hard to optimize with gradient-based updates. This incurs the inconsistency issue between the existing learning objectives and ranking-based evaluation metrics of recommendation models. In this work, we present DRM (differentiable ranking metric) that mitigates the inconsistency and improves recommendation performance, by employing the differentiable relaxation of ranking-based evaluation metrics. Via experiments with several real-world datasets, we demonstrate that the joint learning of the DRM cost function upon existing factor based recommendation models significantly improves the quality of recommendations, in comparison with other state-of-the-art recommendation methods.
A recommender system recommends a few items for a user by sorting items according to their predicted preferences and filter items with the highest predicted preferences. While sorting and selecting top-K items are an inherent part of the personalized recommendation, it is nontrivial to incorporate them in the process of end-to-end model training since sorting is not differentiable and impossible to optimize with gradient based updates. Instead, existing recommenders optimize surrogate objectives, often rendering suboptimal quality of recommendations. In this paper, we propose the differentiable ranking metrics (DRM), a differentiable relaxation of evaluation metrics such as Precision and Recall. DRM maximizes the evaluation metrics for recommendation models directly. Via experiments with several real-world datasets, we demonstrate that the joint learning of the DRM cost function upon existing factor-based recommendation models improves the quality of recommendations significantly, in comparison with other state-of-the-art recommendation methods.