Matches in SemOpenAlex for { <https://semopenalex.org/work/W2214754659> ?p ?o ?g. }
- W2214754659 abstract "Several popular graph embedding techniques for representation learning and dimensionality reduction rely on performing computationally expensive eigendecompositions to derive a nonlinear transformation of the input data space. The resulting eigenvectors encode the embedding coordinates for the training samples only, and so the embedding of novel data samples requires further costly computation. In this paper, we present a method for the out-of-sample extension of graph embeddings using deep neural networks (DNN) to parametrically approximate these nonlinear maps. Compared with traditional nonparametric out-of-sample extension methods, we demonstrate that the DNNs can generalize with equal or better fidelity and require orders of magnitude less computation at test time. Moreover, we find that unsupervised pretraining of the DNNs improves optimization for larger network sizes, thus removing sensitivity to model selection." @default.
- W2214754659 created "2016-06-24" @default.
- W2214754659 creator A5006451413 @default.
- W2214754659 creator A5014425850 @default.
- W2214754659 creator A5046596198 @default.
- W2214754659 date "2015-08-18" @default.
- W2214754659 modified "2023-09-27" @default.
- W2214754659 title "Scalable Out-of-Sample Extension of Graph Embeddings Using Deep Neural Networks" @default.
- W2214754659 cites W1524333225 @default.
- W2214754659 cites W1545920196 @default.
- W2214754659 cites W1872489089 @default.
- W2214754659 cites W2001141328 @default.
- W2214754659 cites W2025482506 @default.
- W2214754659 cites W2053186076 @default.
- W2214754659 cites W2063532964 @default.
- W2214754659 cites W2065136108 @default.
- W2214754659 cites W2068993905 @default.
- W2214754659 cites W2072128103 @default.
- W2214754659 cites W2072219999 @default.
- W2214754659 cites W2082864603 @default.
- W2214754659 cites W2101094502 @default.
- W2214754659 cites W2110798204 @default.
- W2214754659 cites W2117553576 @default.
- W2214754659 cites W2118103795 @default.
- W2214754659 cites W2118571463 @default.
- W2214754659 cites W2125879978 @default.
- W2214754659 cites W2137983211 @default.
- W2214754659 cites W2141566892 @default.
- W2214754659 cites W2149382413 @default.
- W2214754659 cites W2150738795 @default.
- W2214754659 cites W2152386463 @default.
- W2214754659 cites W2153934661 @default.
- W2214754659 cites W2167922717 @default.
- W2214754659 cites W2406820985 @default.
- W2214754659 cites W2798909945 @default.
- W2214754659 cites W3100680744 @default.
- W2214754659 cites W3146803896 @default.
- W2214754659 cites W2136040699 @default.
- W2214754659 hasPublicationYear "2015" @default.
- W2214754659 type Work @default.
- W2214754659 sameAs 2214754659 @default.
- W2214754659 citedByCount "2" @default.
- W2214754659 countsByYear W22147546592017 @default.
- W2214754659 countsByYear W22147546592019 @default.
- W2214754659 crossrefType "posted-content" @default.
- W2214754659 hasAuthorship W2214754659A5006451413 @default.
- W2214754659 hasAuthorship W2214754659A5014425850 @default.
- W2214754659 hasAuthorship W2214754659A5046596198 @default.
- W2214754659 hasConcept C104317684 @default.
- W2214754659 hasConcept C111030470 @default.
- W2214754659 hasConcept C11413529 @default.
- W2214754659 hasConcept C121332964 @default.
- W2214754659 hasConcept C132525143 @default.
- W2214754659 hasConcept C154945302 @default.
- W2214754659 hasConcept C158622935 @default.
- W2214754659 hasConcept C158693339 @default.
- W2214754659 hasConcept C185592680 @default.
- W2214754659 hasConcept C41008148 @default.
- W2214754659 hasConcept C41608201 @default.
- W2214754659 hasConcept C45374587 @default.
- W2214754659 hasConcept C48044578 @default.
- W2214754659 hasConcept C50644808 @default.
- W2214754659 hasConcept C55493867 @default.
- W2214754659 hasConcept C62520636 @default.
- W2214754659 hasConcept C66746571 @default.
- W2214754659 hasConcept C70518039 @default.
- W2214754659 hasConcept C75564084 @default.
- W2214754659 hasConcept C77088390 @default.
- W2214754659 hasConcept C80444323 @default.
- W2214754659 hasConceptScore W2214754659C104317684 @default.
- W2214754659 hasConceptScore W2214754659C111030470 @default.
- W2214754659 hasConceptScore W2214754659C11413529 @default.
- W2214754659 hasConceptScore W2214754659C121332964 @default.
- W2214754659 hasConceptScore W2214754659C132525143 @default.
- W2214754659 hasConceptScore W2214754659C154945302 @default.
- W2214754659 hasConceptScore W2214754659C158622935 @default.
- W2214754659 hasConceptScore W2214754659C158693339 @default.
- W2214754659 hasConceptScore W2214754659C185592680 @default.
- W2214754659 hasConceptScore W2214754659C41008148 @default.
- W2214754659 hasConceptScore W2214754659C41608201 @default.
- W2214754659 hasConceptScore W2214754659C45374587 @default.
- W2214754659 hasConceptScore W2214754659C48044578 @default.
- W2214754659 hasConceptScore W2214754659C50644808 @default.
- W2214754659 hasConceptScore W2214754659C55493867 @default.
- W2214754659 hasConceptScore W2214754659C62520636 @default.
- W2214754659 hasConceptScore W2214754659C66746571 @default.
- W2214754659 hasConceptScore W2214754659C70518039 @default.
- W2214754659 hasConceptScore W2214754659C75564084 @default.
- W2214754659 hasConceptScore W2214754659C77088390 @default.
- W2214754659 hasConceptScore W2214754659C80444323 @default.
- W2214754659 hasLocation W22147546591 @default.
- W2214754659 hasOpenAccess W2214754659 @default.
- W2214754659 hasPrimaryLocation W22147546591 @default.
- W2214754659 hasRelatedWork W1754581914 @default.
- W2214754659 hasRelatedWork W1989880160 @default.
- W2214754659 hasRelatedWork W2137023544 @default.
- W2214754659 hasRelatedWork W2163308540 @default.
- W2214754659 hasRelatedWork W2227768973 @default.
- W2214754659 hasRelatedWork W2346842666 @default.
- W2214754659 hasRelatedWork W2479416251 @default.