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

Nowadays designing a real recommendation system has been a critical problemfor both academic and industry. However, due to the huge number of users anditems, the diversity and dynamic property of the user interest, how to design ascalable recommendation system, which is able to efficiently produce effectiveand diverse recommendation results on billion-scale scenarios, is still achallenging and open problem for existing methods. In this paper, given theuser-item interaction graph, we propose RNE, a data-efficientRecommendation-based Network Embedding method, to give personalized and diverseitems to users. Specifically, we propose a diversity- and dynamics-awareneighbor sampling method for network embedding. On the one hand, the method isable to preserve the local structure between the users and items while modelingthe diversity and dynamic property of the user interest to boost therecommendation quality. On the other hand the sampling method can reduce thecomplexity of the whole method theoretically to make it possible forbillion-scale recommendation. We also implement the designed algorithm in adistributed way to further improves its scalability. Experimentally, we deployRNE on a recommendation scenario of Taobao, the largest E-commerce platform inChina, and train it on a billion-scale user-item graph. As is shown on severalonline metrics on A/B testing, RNE is able to achieve both high-quality anddiverse results compared with CF-based methods. We also conduct the offlineexperiments on Pinterest dataset comparing with several state-of-the-artrecommendation methods and network embedding methods. The results demonstratethat our method is able to produce a good result while runs much faster thanthe baseline methods.

RNE: A Scalable Network Embedding for Billion-scale Recommendation