FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2767993539> ?p ?o ?g. }

• W2767993539 endingPage "4338" @default.
• W2767993539 startingPage "4324" @default.
• W2767993539 abstract "Embedding methods have shown promising performance in multilabel prediction, as they are able to discover the label dependence. However, most methods ignore the correlations between the input and output, such that their learned embeddings are not well aligned, which leads to degradation in prediction performance. This paper presents a formulation for multilabel learning, from the perspective of cross-view learning, that explores the correlations between the input and the output. The proposed method, called Co-Embedding (CoE), jointly learns a semantic common subspace and view-specific mappings within one framework. The semantic similarity structure among the embeddings is further preserved, ensuring that close embeddings share similar labels. Additionally, CoE conducts multilabel prediction through the cross-view <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$k$ </tex-math></inline-formula> nearest neighborhood ( <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$k$ </tex-math></inline-formula> NN) search among the learned embeddings, which significantly reduces computational costs compared with conventional decoding schemes. A hashing-based model, i.e., Co-Hashing (CoH), is further proposed. CoH is based on CoE, and imposes the binary constraint on continuous latent embeddings. CoH aims to generate compact binary representations to improve the prediction efficiency by benefiting from the efficient <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$k$ </tex-math></inline-formula> NN search of multiple labels in the Hamming space. Extensive experiments on various real-world data sets demonstrate the superiority of the proposed methods over the state of the arts in terms of both prediction accuracy and efficiency." @default.
• W2767993539 created "2017-11-17" @default.
• W2767993539 creator A5026283201 @default.
• W2767993539 creator A5034434932 @default.
• W2767993539 creator A5061132796 @default.
• W2767993539 creator A5068243197 @default.
• W2767993539 creator A5091587294 @default.
• W2767993539 date "2018-09-01" @default.
• W2767993539 modified "2023-10-16" @default.
• W2767993539 title "Multilabel Prediction via Cross-View Search" @default.
• W2767993539 cites W1572158434 @default.
• W2767993539 cites W1910300841 @default.
• W2767993539 cites W1969752030 @default.
• W2767993539 cites W1974647172 @default.
• W2767993539 cites W1983010349 @default.
• W2767993539 cites W1985583020 @default.
• W2767993539 cites W1987753869 @default.
• W2767993539 cites W2007972815 @default.
• W2767993539 cites W2027869746 @default.
• W2767993539 cites W2052684427 @default.
• W2767993539 cites W2057069782 @default.
• W2767993539 cites W2061879449 @default.
• W2767993539 cites W2065928620 @default.
• W2767993539 cites W2086953401 @default.
• W2767993539 cites W2106491486 @default.
• W2767993539 cites W2108013467 @default.
• W2767993539 cites W2110588405 @default.
• W2767993539 cites W2114315281 @default.
• W2767993539 cites W2189540548 @default.
• W2767993539 cites W2194775991 @default.
• W2767993539 cites W2203271703 @default.
• W2767993539 cites W2211092169 @default.
• W2767993539 cites W2288560581 @default.
• W2767993539 cites W2336484677 @default.
• W2767993539 cites W2519051215 @default.
• W2767993539 cites W2551647111 @default.
• W2767993539 cites W2586451513 @default.
• W2767993539 cites W2741530248 @default.
• W2767993539 cites W2963213486 @default.
• W2767993539 cites W4236362309 @default.
• W2767993539 cites W55768394 @default.
• W2767993539 doi "https://doi.org/10.1109/tnnls.2017.2763967" @default.
• W2767993539 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29990175" @default.
• W2767993539 hasPublicationYear "2018" @default.
• W2767993539 type Work @default.
• W2767993539 sameAs 2767993539 @default.
• W2767993539 citedByCount "61" @default.
• W2767993539 countsByYear W27679935392018 @default.
• W2767993539 countsByYear W27679935392019 @default.
• W2767993539 countsByYear W27679935392020 @default.
• W2767993539 countsByYear W27679935392021 @default.
• W2767993539 countsByYear W27679935392022 @default.
• W2767993539 countsByYear W27679935392023 @default.
• W2767993539 crossrefType "journal-article" @default.
• W2767993539 hasAuthorship W2767993539A5026283201 @default.
• W2767993539 hasAuthorship W2767993539A5034434932 @default.
• W2767993539 hasAuthorship W2767993539A5061132796 @default.
• W2767993539 hasAuthorship W2767993539A5068243197 @default.
• W2767993539 hasAuthorship W2767993539A5091587294 @default.
• W2767993539 hasConcept C103278499 @default.
• W2767993539 hasConcept C115961682 @default.
• W2767993539 hasConcept C12713177 @default.
• W2767993539 hasConcept C130318100 @default.
• W2767993539 hasConcept C154945302 @default.
• W2767993539 hasConcept C199360897 @default.
• W2767993539 hasConcept C2524010 @default.
• W2767993539 hasConcept C2776036281 @default.
• W2767993539 hasConcept C32834561 @default.
• W2767993539 hasConcept C33923547 @default.
• W2767993539 hasConcept C41008148 @default.
• W2767993539 hasConcept C41608201 @default.
• W2767993539 hasConcept C45357846 @default.
• W2767993539 hasConcept C48372109 @default.
• W2767993539 hasConcept C80444323 @default.
• W2767993539 hasConcept C94375191 @default.
• W2767993539 hasConcept C99138194 @default.
• W2767993539 hasConceptScore W2767993539C103278499 @default.
• W2767993539 hasConceptScore W2767993539C115961682 @default.
• W2767993539 hasConceptScore W2767993539C12713177 @default.
• W2767993539 hasConceptScore W2767993539C130318100 @default.
• W2767993539 hasConceptScore W2767993539C154945302 @default.
• W2767993539 hasConceptScore W2767993539C199360897 @default.
• W2767993539 hasConceptScore W2767993539C2524010 @default.
• W2767993539 hasConceptScore W2767993539C2776036281 @default.
• W2767993539 hasConceptScore W2767993539C32834561 @default.
• W2767993539 hasConceptScore W2767993539C33923547 @default.
• W2767993539 hasConceptScore W2767993539C41008148 @default.
• W2767993539 hasConceptScore W2767993539C41608201 @default.
• W2767993539 hasConceptScore W2767993539C45357846 @default.
• W2767993539 hasConceptScore W2767993539C48372109 @default.
• W2767993539 hasConceptScore W2767993539C80444323 @default.
• W2767993539 hasConceptScore W2767993539C94375191 @default.
• W2767993539 hasConceptScore W2767993539C99138194 @default.
• W2767993539 hasFunder F4320321001 @default.
• W2767993539 hasIssue "9" @default.
• W2767993539 hasLocation W27679935391 @default.
• W2767993539 hasLocation W27679935392 @default.
• W2767993539 hasOpenAccess W2767993539 @default.

• next