Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387398146> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4387398146 endingPage "121875" @default.
- W4387398146 startingPage "121875" @default.
- W4387398146 abstract "Learning how to represent users based on historical interactions is a crucial problem for recommender systems. Unavoidable noise in interactions and long-tail items composed of a large number of unpopular items bring more challenges for learning better user representations and still limit the performance of existing models. Aiming to design a simple model that can alleviate both the noise problem and the long-tail item problem, we propose a Hybrid Normalization strategy via feature statistics for Collaborative Filtering (HyNCF). After each user is represented by his/her interacted items, the feature statistics of a target user are mixed with that of another randomly sampled user. In addition, the uncertainty estimation of the target user’s feature statistics is calculated by a Gaussian sampling technique. Both kinds of improved feature statistics are separately used to normalize the target user’s embedding, and then normalized embeddings are aggregated to generate two representations of the user. Based on the fusion of the two representations, the cosine contrastive loss is used to train HyNCF. The effectiveness of the proposed model is evaluated on five benchmark datasets." @default.
- W4387398146 created "2023-10-07" @default.
- W4387398146 creator A5060502085 @default.
- W4387398146 creator A5062182674 @default.
- W4387398146 creator A5079270412 @default.
- W4387398146 creator A5090390841 @default.
- W4387398146 date "2023-10-01" @default.
- W4387398146 modified "2023-10-07" @default.
- W4387398146 title "HyNCF: A hybrid normalization strategy via feature statistics for collaborative filtering" @default.
- W4387398146 cites W2054141820 @default.
- W4387398146 cites W2802187397 @default.
- W4387398146 cites W3014073192 @default.
- W4387398146 cites W3195184248 @default.
- W4387398146 cites W3196402383 @default.
- W4387398146 cites W4206974132 @default.
- W4387398146 cites W4296640362 @default.
- W4387398146 cites W4306928146 @default.
- W4387398146 cites W4310137660 @default.
- W4387398146 doi "https://doi.org/10.1016/j.eswa.2023.121875" @default.
- W4387398146 hasPublicationYear "2023" @default.
- W4387398146 type Work @default.
- W4387398146 citedByCount "0" @default.
- W4387398146 crossrefType "journal-article" @default.
- W4387398146 hasAuthorship W4387398146A5060502085 @default.
- W4387398146 hasAuthorship W4387398146A5062182674 @default.
- W4387398146 hasAuthorship W4387398146A5079270412 @default.
- W4387398146 hasAuthorship W4387398146A5090390841 @default.
- W4387398146 hasConcept C119857082 @default.
- W4387398146 hasConcept C121332964 @default.
- W4387398146 hasConcept C124101348 @default.
- W4387398146 hasConcept C13280743 @default.
- W4387398146 hasConcept C136886441 @default.
- W4387398146 hasConcept C138885662 @default.
- W4387398146 hasConcept C144024400 @default.
- W4387398146 hasConcept C153180895 @default.
- W4387398146 hasConcept C154945302 @default.
- W4387398146 hasConcept C163716315 @default.
- W4387398146 hasConcept C185798385 @default.
- W4387398146 hasConcept C19165224 @default.
- W4387398146 hasConcept C205649164 @default.
- W4387398146 hasConcept C21569690 @default.
- W4387398146 hasConcept C2776401178 @default.
- W4387398146 hasConcept C41008148 @default.
- W4387398146 hasConcept C41608201 @default.
- W4387398146 hasConcept C41895202 @default.
- W4387398146 hasConcept C557471498 @default.
- W4387398146 hasConcept C59404180 @default.
- W4387398146 hasConcept C62520636 @default.
- W4387398146 hasConceptScore W4387398146C119857082 @default.
- W4387398146 hasConceptScore W4387398146C121332964 @default.
- W4387398146 hasConceptScore W4387398146C124101348 @default.
- W4387398146 hasConceptScore W4387398146C13280743 @default.
- W4387398146 hasConceptScore W4387398146C136886441 @default.
- W4387398146 hasConceptScore W4387398146C138885662 @default.
- W4387398146 hasConceptScore W4387398146C144024400 @default.
- W4387398146 hasConceptScore W4387398146C153180895 @default.
- W4387398146 hasConceptScore W4387398146C154945302 @default.
- W4387398146 hasConceptScore W4387398146C163716315 @default.
- W4387398146 hasConceptScore W4387398146C185798385 @default.
- W4387398146 hasConceptScore W4387398146C19165224 @default.
- W4387398146 hasConceptScore W4387398146C205649164 @default.
- W4387398146 hasConceptScore W4387398146C21569690 @default.
- W4387398146 hasConceptScore W4387398146C2776401178 @default.
- W4387398146 hasConceptScore W4387398146C41008148 @default.
- W4387398146 hasConceptScore W4387398146C41608201 @default.
- W4387398146 hasConceptScore W4387398146C41895202 @default.
- W4387398146 hasConceptScore W4387398146C557471498 @default.
- W4387398146 hasConceptScore W4387398146C59404180 @default.
- W4387398146 hasConceptScore W4387398146C62520636 @default.
- W4387398146 hasLocation W43873981461 @default.
- W4387398146 hasOpenAccess W4387398146 @default.
- W4387398146 hasPrimaryLocation W43873981461 @default.
- W4387398146 hasRelatedWork W1484355083 @default.
- W4387398146 hasRelatedWork W2041004656 @default.
- W4387398146 hasRelatedWork W2098758514 @default.
- W4387398146 hasRelatedWork W2103058005 @default.
- W4387398146 hasRelatedWork W2119611366 @default.
- W4387398146 hasRelatedWork W2170391450 @default.
- W4387398146 hasRelatedWork W2202724490 @default.
- W4387398146 hasRelatedWork W2735929803 @default.
- W4387398146 hasRelatedWork W3008845055 @default.
- W4387398146 hasRelatedWork W4220714703 @default.
- W4387398146 isParatext "false" @default.
- W4387398146 isRetracted "false" @default.
- W4387398146 workType "article" @default.