English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Rating prediction is a core problem in recommender systems to quantify user'spreferences towards items, however, rating imbalance naturally roots inreal-world user ratings that cause biased predictions and lead to poorperformance on tail ratings. While existing approaches in the rating predictiontask deploy weighted cross-entropy to re-weight training samples, suchapproaches commonly assume an normal distribution, a symmetrical and balancedspace. 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 andaugment feature representations by the Gumbel distributions. We propose aGumbel-based variational encoder to transform features into non-normal vectorspace. Second, we deploy a multi-scale convolutional fusion network tointegrate comprehensive views of users and items from the rating matrix anduser reviews. Third, we adopt a skip connection module to personalize finalrating predictions. We conduct extensive experiments on five datasets with botherror- and ranking-based metrics. Experiments on ranking and regressionevaluation tasks prove that the GVN can effectively achieve state-of-the-artperformance across the datasets and reduce the biased predictions of tailratings. We compare with various distributions (e.g., normal and Poisson) anddemonstrate the effectiveness of Gumbel-based methods on class-imbalancemodeling.

A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation