Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320341726> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4320341726 abstract "With the increase of content pages and interactive buttons in online services such as online-shopping and video-watching websites, industrial-scale recommender systems face challenges in multi-domain and multi-task recommendations. The core of multi-task and multi-domain recommendation is to accurately capture user interests in multiple scenarios given multiple user behaviors. In this paper, we propose a plug-and-play textit{textbf{P}arameter and textbf{E}mbedding textbf{P}ersonalized textbf{Net}work (textbf{PEPNet})} for multi-domain and multi-task recommendation. PEPNet takes personalized prior information as input and dynamically scales the bottom-level Embedding and top-level DNN hidden units through gate mechanisms. textit{Embedding Personalized Network (EPNet)} performs personalized selection on Embedding to fuse features with different importance for different users in multiple domains. textit{Parameter Personalized Network (PPNet)} executes personalized modification on DNN parameters to balance targets with different sparsity for different users in multiple tasks. We have made a series of special engineering optimizations combining the Kuaishou training framework and the online deployment environment. By infusing personalized selection of Embedding and personalized modification of DNN parameters, PEPNet tailored to the interests of each individual obtains significant performance gains, with online improvements exceeding 1% in multiple task metrics across multiple domains. We have deployed PEPNet in Kuaishou apps, serving over 300 million users every day." @default.
- W4320341726 created "2023-02-13" @default.
- W4320341726 creator A5006466867 @default.
- W4320341726 creator A5018109582 @default.
- W4320341726 creator A5048432969 @default.
- W4320341726 creator A5062939922 @default.
- W4320341726 creator A5063163595 @default.
- W4320341726 creator A5065240810 @default.
- W4320341726 creator A5066401817 @default.
- W4320341726 date "2023-02-02" @default.
- W4320341726 modified "2023-10-16" @default.
- W4320341726 title "PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information" @default.
- W4320341726 doi "https://doi.org/10.48550/arxiv.2302.01115" @default.
- W4320341726 hasPublicationYear "2023" @default.
- W4320341726 type Work @default.
- W4320341726 citedByCount "0" @default.
- W4320341726 crossrefType "posted-content" @default.
- W4320341726 hasAuthorship W4320341726A5006466867 @default.
- W4320341726 hasAuthorship W4320341726A5018109582 @default.
- W4320341726 hasAuthorship W4320341726A5048432969 @default.
- W4320341726 hasAuthorship W4320341726A5062939922 @default.
- W4320341726 hasAuthorship W4320341726A5063163595 @default.
- W4320341726 hasAuthorship W4320341726A5065240810 @default.
- W4320341726 hasAuthorship W4320341726A5066401817 @default.
- W4320341726 hasBestOaLocation W43203417261 @default.
- W4320341726 hasConcept C105339364 @default.
- W4320341726 hasConcept C107457646 @default.
- W4320341726 hasConcept C111919701 @default.
- W4320341726 hasConcept C119857082 @default.
- W4320341726 hasConcept C134306372 @default.
- W4320341726 hasConcept C154945302 @default.
- W4320341726 hasConcept C162324750 @default.
- W4320341726 hasConcept C187736073 @default.
- W4320341726 hasConcept C2164484 @default.
- W4320341726 hasConcept C23123220 @default.
- W4320341726 hasConcept C2780451532 @default.
- W4320341726 hasConcept C33923547 @default.
- W4320341726 hasConcept C36503486 @default.
- W4320341726 hasConcept C41008148 @default.
- W4320341726 hasConcept C41608201 @default.
- W4320341726 hasConcept C557471498 @default.
- W4320341726 hasConcept C76155785 @default.
- W4320341726 hasConcept C81917197 @default.
- W4320341726 hasConceptScore W4320341726C105339364 @default.
- W4320341726 hasConceptScore W4320341726C107457646 @default.
- W4320341726 hasConceptScore W4320341726C111919701 @default.
- W4320341726 hasConceptScore W4320341726C119857082 @default.
- W4320341726 hasConceptScore W4320341726C134306372 @default.
- W4320341726 hasConceptScore W4320341726C154945302 @default.
- W4320341726 hasConceptScore W4320341726C162324750 @default.
- W4320341726 hasConceptScore W4320341726C187736073 @default.
- W4320341726 hasConceptScore W4320341726C2164484 @default.
- W4320341726 hasConceptScore W4320341726C23123220 @default.
- W4320341726 hasConceptScore W4320341726C2780451532 @default.
- W4320341726 hasConceptScore W4320341726C33923547 @default.
- W4320341726 hasConceptScore W4320341726C36503486 @default.
- W4320341726 hasConceptScore W4320341726C41008148 @default.
- W4320341726 hasConceptScore W4320341726C41608201 @default.
- W4320341726 hasConceptScore W4320341726C557471498 @default.
- W4320341726 hasConceptScore W4320341726C76155785 @default.
- W4320341726 hasConceptScore W4320341726C81917197 @default.
- W4320341726 hasLocation W43203417261 @default.
- W4320341726 hasOpenAccess W4320341726 @default.
- W4320341726 hasPrimaryLocation W43203417261 @default.
- W4320341726 hasRelatedWork W1504101963 @default.
- W4320341726 hasRelatedWork W1721086902 @default.
- W4320341726 hasRelatedWork W2180505379 @default.
- W4320341726 hasRelatedWork W2393430015 @default.
- W4320341726 hasRelatedWork W2469392158 @default.
- W4320341726 hasRelatedWork W2576496345 @default.
- W4320341726 hasRelatedWork W2743342830 @default.
- W4320341726 hasRelatedWork W2955042007 @default.
- W4320341726 hasRelatedWork W3136554434 @default.
- W4320341726 hasRelatedWork W4382318872 @default.
- W4320341726 isParatext "false" @default.
- W4320341726 isRetracted "false" @default.
- W4320341726 workType "article" @default.