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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Generally speaking, the model training for recommender systems can be basedon two types of data, namely explicit feedback and implicit feedback. Moreover,because of its general availability, we see wide adoption of implicit feedbackdata, such as click signal. There are mainly two challenges for the applicationof implicit feedback. First, implicit data just includes positive feedback.Therefore, we are not sure whether the non-interacted items are really negativeor positive but not displayed to the corresponding user. Moreover, therelevance of rare items is usually underestimated since much fewer positivefeedback of rare items is collected compared with popular ones. To tackle suchdifficulties, both pointwise and pairwise solutions are proposed before forunbiased relevance learning. As pairwise learning suits well for the rankingtasks, the previously proposed unbiased pairwise learning algorithm alreadyachieves state-of-the-art performance. Nonetheless, the existing unbiasedpairwise learning method suffers from high variance. To get satisfactoryperformance, non-negative estimator is utilized for practical variance controlbut introduces additional bias. In this work, we propose an unbiased pairwiselearning method, named UPL, with much lower variance to learn a truly unbiasedrecommender model. Extensive offline experiments on real world datasets andonline A/B testing demonstrate the superior performance of our proposed method.

Unbiased Pairwise Learning from Implicit Feedback for Recommender Systems without Biased Variance Control