FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907907589> ?p ?o ?g. }

• W2907907589 endingPage "139" @default.
• W2907907589 startingPage "132" @default.
• W2907907589 abstract "The recommendation algorithm is attracting increasing attention in analyzing big data. Matrix factorization (MF) is one of the recommendation methods and Singular Value Decomposition (SVD) is the most popular matrix factorization method. However, the existing SVD methods usually initialize user and item feature randomly, not fully utilize the information of the data, so require plenty of experiments to determine feature matrix dimension, with low convergence efficiency and low accuracy. This paper presents a hybrid initialization method based on attribute mapping and autoencoder neural network to solve these problems, which consists of three parts: (1) use the number of item attribute types to determine feature matrix dimension in order to avoid multiple experiments to select the optimal dimension value; (2) use items’ attributes to initialize the item feature matrix in SVD＋＋, and use an attribute mapping mechanism to get an item feature vector by fitting the rating matrix to accelerate the convergence; (3) adopt the autoencoder neural network to reduce feature dimension and obtain item latent features for initializing SVD＋＋. The experimental results show that our methods achieve better performance than SVD＋＋ random initialization and also be adopted to other matrix factorization methods." @default.
• W2907907589 created "2019-01-11" @default.
• W2907907589 creator A5012610630 @default.
• W2907907589 creator A5022528124 @default.
• W2907907589 creator A5054412130 @default.
• W2907907589 creator A5059670077 @default.
• W2907907589 creator A5072694505 @default.
• W2907907589 creator A5074998105 @default.
• W2907907589 creator A5091551174 @default.
• W2907907589 date "2019-02-01" @default.
• W2907907589 modified "2023-10-14" @default.
• W2907907589 title "Attribute mapping and autoencoder neural network based matrix factorization initialization for recommendation systems" @default.
• W2907907589 cites W1483439930 @default.
• W2907907589 cites W1966743391 @default.
• W2907907589 cites W2002519017 @default.
• W2907907589 cites W2015583498 @default.
• W2907907589 cites W2053101055 @default.
• W2907907589 cites W2054141820 @default.
• W2907907589 cites W2064637959 @default.
• W2907907589 cites W2245341025 @default.
• W2907907589 cites W2315503695 @default.
• W2907907589 cites W2398365891 @default.
• W2907907589 cites W2519368133 @default.
• W2907907589 cites W2519400179 @default.
• W2907907589 cites W2533696134 @default.
• W2907907589 cites W2609105278 @default.
• W2907907589 cites W2762460055 @default.
• W2907907589 cites W2890607553 @default.
• W2907907589 doi "https://doi.org/10.1016/j.knosys.2018.12.022" @default.
• W2907907589 hasPublicationYear "2019" @default.
• W2907907589 type Work @default.
• W2907907589 sameAs 2907907589 @default.
• W2907907589 citedByCount "38" @default.
• W2907907589 countsByYear W29079075892020 @default.
• W2907907589 countsByYear W29079075892021 @default.
• W2907907589 countsByYear W29079075892022 @default.
• W2907907589 countsByYear W29079075892023 @default.
• W2907907589 crossrefType "journal-article" @default.
• W2907907589 hasAuthorship W2907907589A5012610630 @default.
• W2907907589 hasAuthorship W2907907589A5022528124 @default.
• W2907907589 hasAuthorship W2907907589A5054412130 @default.
• W2907907589 hasAuthorship W2907907589A5059670077 @default.
• W2907907589 hasAuthorship W2907907589A5072694505 @default.
• W2907907589 hasAuthorship W2907907589A5074998105 @default.
• W2907907589 hasAuthorship W2907907589A5091551174 @default.
• W2907907589 hasConcept C101738243 @default.
• W2907907589 hasConcept C106487976 @default.
• W2907907589 hasConcept C11413529 @default.
• W2907907589 hasConcept C114466953 @default.
• W2907907589 hasConcept C119857082 @default.
• W2907907589 hasConcept C121332964 @default.
• W2907907589 hasConcept C124101348 @default.
• W2907907589 hasConcept C138885662 @default.
• W2907907589 hasConcept C152671427 @default.
• W2907907589 hasConcept C153180895 @default.
• W2907907589 hasConcept C154945302 @default.
• W2907907589 hasConcept C158693339 @default.
• W2907907589 hasConcept C159985019 @default.
• W2907907589 hasConcept C162324750 @default.
• W2907907589 hasConcept C192562407 @default.
• W2907907589 hasConcept C199360897 @default.
• W2907907589 hasConcept C202444582 @default.
• W2907907589 hasConcept C21569690 @default.
• W2907907589 hasConcept C22789450 @default.
• W2907907589 hasConcept C2776401178 @default.
• W2907907589 hasConcept C2777303404 @default.
• W2907907589 hasConcept C33676613 @default.
• W2907907589 hasConcept C33923547 @default.
• W2907907589 hasConcept C41008148 @default.
• W2907907589 hasConcept C41895202 @default.
• W2907907589 hasConcept C42355184 @default.
• W2907907589 hasConcept C50522688 @default.
• W2907907589 hasConcept C50644808 @default.
• W2907907589 hasConcept C557471498 @default.
• W2907907589 hasConcept C62520636 @default.
• W2907907589 hasConcept C83665646 @default.
• W2907907589 hasConceptScore W2907907589C101738243 @default.
• W2907907589 hasConceptScore W2907907589C106487976 @default.
• W2907907589 hasConceptScore W2907907589C11413529 @default.
• W2907907589 hasConceptScore W2907907589C114466953 @default.
• W2907907589 hasConceptScore W2907907589C119857082 @default.
• W2907907589 hasConceptScore W2907907589C121332964 @default.
• W2907907589 hasConceptScore W2907907589C124101348 @default.
• W2907907589 hasConceptScore W2907907589C138885662 @default.
• W2907907589 hasConceptScore W2907907589C152671427 @default.
• W2907907589 hasConceptScore W2907907589C153180895 @default.
• W2907907589 hasConceptScore W2907907589C154945302 @default.
• W2907907589 hasConceptScore W2907907589C158693339 @default.
• W2907907589 hasConceptScore W2907907589C159985019 @default.
• W2907907589 hasConceptScore W2907907589C162324750 @default.
• W2907907589 hasConceptScore W2907907589C192562407 @default.
• W2907907589 hasConceptScore W2907907589C199360897 @default.
• W2907907589 hasConceptScore W2907907589C202444582 @default.
• W2907907589 hasConceptScore W2907907589C21569690 @default.
• W2907907589 hasConceptScore W2907907589C22789450 @default.
• W2907907589 hasConceptScore W2907907589C2776401178 @default.
• W2907907589 hasConceptScore W2907907589C2777303404 @default.
• W2907907589 hasConceptScore W2907907589C33676613 @default.

• next