GRP: A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation

Rating prediction is a core problem in recommender systems to quantify users preferences towards different items. Due to the imbalanced rating distributions in training data, existing recommendation methods suffer from the biased prediction problem that generates biased prediction results. Thus, their performance on predicting ratings which rarely appear in training data is unsatisfactory. In this paper, inspired by the superior capability of Extreme Value Distribution (EVD)-based methods in modeling the distribution of rare data, we propose a novel \underline{\emph{G}}umbel Distribution-based \underline{\emph{R}}ating \underline{\emph{P}}rediction framework (GRP) which can accurately predict both frequent and rare ratings between users and items. In our approach, we first define different Gumbel distributions for each rating level, which can be learned by historical rating statistics of users and items. Second, we incorporate the Gumbel-based representations of users and items with their original representations learned from the rating matrix and/or reviews to enrich the representations of users and items via a proposed multi-scale convolutional fusion layer. Third, we propose a data-driven rating prediction module to predict the ratings of user-item pairs. It's worthy to note that our approach can be readily applied to existing recommendation methods for addressing their biased prediction problem. To verify the effectiveness of GRP, we conduct extensive experiments on eight benchmark datasets. Compared with several baseline models, the results show that: 1) GRP achieves state-of-the-art overall performance on all eight datasets; 2) GRP makes a substantial improvement in predicting rare ratings, which shows the effectiveness of our model in addressing the bias prediction problem.