FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380136404> ?p ?o ?g. }

• W4380136404 abstract "Ranking model plays an essential role in e-commerce search and recommendation. An effective ranking model should give a personalized ranking list for each user according to the user preference. Existing algorithms usually extract a user representation vector from the user behavior sequence, then feed the vector into a feed-forward network (FFN) together with other features for feature interactions, and finally produce a personalized ranking score. Despite tremendous progress in the past, there is still room for improvement. Firstly, the personalized patterns of feature interactions for different users are not explicitly modeled. Secondly, most of existing algorithms have poor personalized ranking results for long-tail users with few historical behaviors due to the data sparsity. To overcome the two challenges, we propose Attention Weighted Mixture of Experts (AW-MoE) with contrastive learning for personalized ranking. Firstly, AW-MoE leverages the MoE framework to capture personalized feature interactions for different users. To model the user preference, the user behavior sequence is simultaneously fed into expert networks and the gate network. Within the gate network, one gate unit and one activation unit are designed to adaptively learn the fine-grained activation vector for experts using an attention mechanism. Secondly, a random masking strategy is applied to the user behavior sequence to simulate long-tail users, and an auxiliary contrastive loss is imposed to the output of the gate network to improve the model generalization for these users. This is validated by a higher performance gain on the long-tail user test set. Experiment results on a JD real production dataset and a public dataset demonstrate the effectiveness of AW-MoE, which significantly outperforms state-of-art methods. Notably, AW-MoE has been successfully deployed in the JD e-commerce search engine, ..." @default.
• W4380136404 created "2023-06-10" @default.
• W4380136404 creator A5016338405 @default.
• W4380136404 creator A5017358664 @default.
• W4380136404 creator A5040647242 @default.
• W4380136404 creator A5045596194 @default.
• W4380136404 creator A5063258475 @default.
• W4380136404 creator A5069403876 @default.
• W4380136404 creator A5072367863 @default.
• W4380136404 creator A5073032098 @default.
• W4380136404 creator A5074529126 @default.
• W4380136404 creator A5076299083 @default.
• W4380136404 date "2023-06-08" @default.
• W4380136404 modified "2023-09-28" @default.
• W4380136404 title "Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce" @default.
• W4380136404 doi "https://doi.org/10.48550/arxiv.2306.05011" @default.
• W4380136404 hasPublicationYear "2023" @default.
• W4380136404 type Work @default.
• W4380136404 citedByCount "0" @default.
• W4380136404 crossrefType "posted-content" @default.
• W4380136404 hasAuthorship W4380136404A5016338405 @default.
• W4380136404 hasAuthorship W4380136404A5017358664 @default.
• W4380136404 hasAuthorship W4380136404A5040647242 @default.
• W4380136404 hasAuthorship W4380136404A5045596194 @default.
• W4380136404 hasAuthorship W4380136404A5063258475 @default.
• W4380136404 hasAuthorship W4380136404A5069403876 @default.
• W4380136404 hasAuthorship W4380136404A5072367863 @default.
• W4380136404 hasAuthorship W4380136404A5073032098 @default.
• W4380136404 hasAuthorship W4380136404A5074529126 @default.
• W4380136404 hasAuthorship W4380136404A5076299083 @default.
• W4380136404 hasBestOaLocation W43801364041 @default.
• W4380136404 hasConcept C105795698 @default.
• W4380136404 hasConcept C108583219 @default.
• W4380136404 hasConcept C119857082 @default.
• W4380136404 hasConcept C124101348 @default.
• W4380136404 hasConcept C127413603 @default.
• W4380136404 hasConcept C134306372 @default.
• W4380136404 hasConcept C136764020 @default.
• W4380136404 hasConcept C138885662 @default.
• W4380136404 hasConcept C154945302 @default.
• W4380136404 hasConcept C177148314 @default.
• W4380136404 hasConcept C177264268 @default.
• W4380136404 hasConcept C183003079 @default.
• W4380136404 hasConcept C186625053 @default.
• W4380136404 hasConcept C189430467 @default.
• W4380136404 hasConcept C199360897 @default.
• W4380136404 hasConcept C201995342 @default.
• W4380136404 hasConcept C2776401178 @default.
• W4380136404 hasConcept C2778112365 @default.
• W4380136404 hasConcept C2778827112 @default.
• W4380136404 hasConcept C2780451532 @default.
• W4380136404 hasConcept C2781249084 @default.
• W4380136404 hasConcept C33923547 @default.
• W4380136404 hasConcept C35639132 @default.
• W4380136404 hasConcept C41008148 @default.
• W4380136404 hasConcept C41895202 @default.
• W4380136404 hasConcept C54355233 @default.
• W4380136404 hasConcept C83665646 @default.
• W4380136404 hasConcept C86803240 @default.
• W4380136404 hasConceptScore W4380136404C105795698 @default.
• W4380136404 hasConceptScore W4380136404C108583219 @default.
• W4380136404 hasConceptScore W4380136404C119857082 @default.
• W4380136404 hasConceptScore W4380136404C124101348 @default.
• W4380136404 hasConceptScore W4380136404C127413603 @default.
• W4380136404 hasConceptScore W4380136404C134306372 @default.
• W4380136404 hasConceptScore W4380136404C136764020 @default.
• W4380136404 hasConceptScore W4380136404C138885662 @default.
• W4380136404 hasConceptScore W4380136404C154945302 @default.
• W4380136404 hasConceptScore W4380136404C177148314 @default.
• W4380136404 hasConceptScore W4380136404C177264268 @default.
• W4380136404 hasConceptScore W4380136404C183003079 @default.
• W4380136404 hasConceptScore W4380136404C186625053 @default.
• W4380136404 hasConceptScore W4380136404C189430467 @default.
• W4380136404 hasConceptScore W4380136404C199360897 @default.
• W4380136404 hasConceptScore W4380136404C201995342 @default.
• W4380136404 hasConceptScore W4380136404C2776401178 @default.
• W4380136404 hasConceptScore W4380136404C2778112365 @default.
• W4380136404 hasConceptScore W4380136404C2778827112 @default.
• W4380136404 hasConceptScore W4380136404C2780451532 @default.
• W4380136404 hasConceptScore W4380136404C2781249084 @default.
• W4380136404 hasConceptScore W4380136404C33923547 @default.
• W4380136404 hasConceptScore W4380136404C35639132 @default.
• W4380136404 hasConceptScore W4380136404C41008148 @default.
• W4380136404 hasConceptScore W4380136404C41895202 @default.
• W4380136404 hasConceptScore W4380136404C54355233 @default.
• W4380136404 hasConceptScore W4380136404C83665646 @default.
• W4380136404 hasConceptScore W4380136404C86803240 @default.
• W4380136404 hasLocation W43801364041 @default.
• W4380136404 hasOpenAccess W4380136404 @default.
• W4380136404 hasPrimaryLocation W43801364041 @default.
• W4380136404 hasRelatedWork W1666839187 @default.
• W4380136404 hasRelatedWork W2005318905 @default.
• W4380136404 hasRelatedWork W2494490446 @default.
• W4380136404 hasRelatedWork W2963749793 @default.
• W4380136404 hasRelatedWork W2987487076 @default.
• W4380136404 hasRelatedWork W3004397819 @default.
• W4380136404 hasRelatedWork W3026137317 @default.
• W4380136404 hasRelatedWork W3095121312 @default.
• W4380136404 hasRelatedWork W3200179079 @default.
• W4380136404 hasRelatedWork W4285140884 @default.

• next