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

Recommendation system algorithm based on multi-task learning (MTL) is themajor method for Internet operators to understand users and predict theirbehaviors in the multi-behavior scenario of platform. Task correlation is animportant consideration of MTL goals, traditional models use shared-bottommodels and gating experts to realize shared representation learning andinformation differentiation. However, The relationship between real-world tasksis often more complex than existing methods do not handle properly sharinginformation. In this paper, we propose an Different Expression ParallelHeterogeneous Network (DEPHN) to model multiple tasks simultaneously. DEPHNconstructs the experts at the bottom of the model by using different featureinteraction methods to improve the generalization ability of the sharedinformation flow. In view of the model's differentiating ability for differenttask information flows, DEPHN uses feature explicit mapping and virtualgradient coefficient for expert gating during the training process, andadaptively adjusts the learning intensity of the gated unit by considering thedifference of gating values and task correlation. Extensive experiments onartificial and real-world datasets demonstrate that our proposed method cancapture task correlation in complex situations and achieve better performancethan baseline models\footnote{Accepted in IJCNN2023}.

DEPHN: Different Expression Parallel Heterogeneous Network using virtual gradient optimization for Multi-task Learning