A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation

TL;DR

This paper introduces a Gumbel-based variational network framework for rating prediction in recommender systems, effectively addressing rating imbalance and improving performance on tail ratings through novel distribution modeling and feature augmentation.

Contribution

The paper proposes a Gumbel-based variational encoder and multi-scale fusion network to model rating imbalance and enhance feature representations, outperforming traditional methods assuming normal distributions.

Findings

Achieves state-of-the-art performance on five datasets.

Effectively reduces bias in tail rating predictions.

Demonstrates superiority of Gumbel-based modeling over normal and Poisson distributions.

Abstract

Rating prediction is a core problem in recommender systems to quantify user's preferences towards items, however, rating imbalance naturally roots in real-world user ratings that cause biased predictions and lead to poor performance on tail ratings. While existing approaches in the rating prediction task deploy weighted cross-entropy to re-weight training samples, such approaches commonly assume an normal distribution, a symmetrical and balanced space. In contrast to the normal assumption, we propose a novel \underline{\emph{G}}umbel-based \underline{\emph{V}}ariational \underline{\emph{N}}etwork framework (GVN) to model rating imbalance and augment feature representations by the Gumbel distributions. We propose a Gumbel-based variational encoder to transform features into non-normal vector space. Second, we deploy a multi-scale convolutional fusion network to integrate comprehensive views of users and items from the rating matrix and user reviews. Third, we adopt a skip connection module to personalize final rating predictions. We conduct extensive experiments on five datasets with both error- and ranking-based metrics. Experiments on ranking and regression evaluation tasks prove that the GVN can effectively achieve state-of-the-art performance across the datasets and reduce the biased predictions of tail ratings. We compare with various distributions (e.g., normal and Poisson) and demonstrate the effectiveness of Gumbel-based methods on class-imbalance modeling.