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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In one-class recommendation systems, the goal is to learn a model from asmall set of interacted users and items and then identify thepositively-related user-item pairs among a large number of pairs with unknowninteractions. Most previous loss functions rely on dissimilar pairs of usersand items, which are selected from the ones with unknown interactions, toobtain better prediction performance. This strategy introduces severalchallenges such as increasing training time and hurting the performance bypicking "similar pairs with the unknown interactions" as dissimilar pairs. Inthis paper, the goal is to only use the similar set to train the models. Wepoint out three trivial solutions that the models converge to when they aretrained only on similar pairs: collapsed, partially collapsed, and shrinkingsolutions. We propose two terms that can be added to the objective functions inthe literature to avoid these solutions. The first one is a hinge pairwisedistance loss that avoids the shrinking and collapsed solutions by keeping theaverage pairwise distance of all the representations greater than a margin. Thesecond one is an orthogonality term that minimizes the correlation between thedimensions of the representations and avoids the partially collapsed solution.We conduct experiments on a variety of tasks on public and real-world datasets.The results show that our approach using only similar pairs outperformsstate-of-the-art methods using similar pairs and a large number of dissimilarpairs.

One-class Recommendation Systems with the Hinge Pairwise Distance Loss and Orthogonal Representations