Matches in SemOpenAlex for { <https://semopenalex.org/work/W2966705583> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2966705583 abstract "Deep autoencoder is widely used in dimensionality reduction because of the expressive power of the neural network. Therefore, it is naturally suitable for embedding tasks, which essentially compresses high-dimensional information into a low-dimensional latent space. In terms of network representation, methods based on autoencoder such as SDNE and DNGR have achieved comparable results with the state-of-arts. However, all of them do not leverage label information, which leads to the embeddings lack the characteristic of discrimination. In this paper, we present Triplet Enhanced AutoEncoder (TEA), a new deep network embedding approach from the perspective of metric learning. Equipped with the triplet-loss constraint, the proposed approach not only allows capturing the topological structure but also preserving the discriminative information. Moreover, unlike existing discriminative embedding techniques, TEA is independent of any specific classifier, we call it the model-free property. Extensive empirical results on three public datasets (i.e, Cora, Citeseer and BlogCatalog) show that TEA is stable and achieves state-of-the-art performance compared with both supervised and unsupervised network embedding approaches on various percentages of labeled data. The source code can be obtained from https://github.com/yybeta/TEA." @default.
- W2966705583 created "2019-08-13" @default.
- W2966705583 creator A5014641216 @default.
- W2966705583 creator A5042782010 @default.
- W2966705583 creator A5088843448 @default.
- W2966705583 date "2019-08-01" @default.
- W2966705583 modified "2023-10-14" @default.
- W2966705583 title "Triplet Enhanced AutoEncoder: Model-free Discriminative Network Embedding" @default.
- W2966705583 cites W1949591461 @default.
- W2966705583 cites W1971955426 @default.
- W2966705583 cites W2090891622 @default.
- W2966705583 cites W2106053110 @default.
- W2966705583 cites W2125031621 @default.
- W2966705583 cites W2153579005 @default.
- W2966705583 cites W2164359548 @default.
- W2966705583 cites W2242161203 @default.
- W2966705583 cites W2250539671 @default.
- W2966705583 cites W2393319904 @default.
- W2966705583 cites W2574817444 @default.
- W2966705583 cites W2579372251 @default.
- W2966705583 cites W2604366058 @default.
- W2966705583 cites W2624431344 @default.
- W2966705583 cites W2962756421 @default.
- W2966705583 cites W2963224980 @default.
- W2966705583 doi "https://doi.org/10.24963/ijcai.2019/745" @default.
- W2966705583 hasPublicationYear "2019" @default.
- W2966705583 type Work @default.
- W2966705583 sameAs 2966705583 @default.
- W2966705583 citedByCount "24" @default.
- W2966705583 countsByYear W29667055832012 @default.
- W2966705583 countsByYear W29667055832020 @default.
- W2966705583 countsByYear W29667055832021 @default.
- W2966705583 countsByYear W29667055832022 @default.
- W2966705583 countsByYear W29667055832023 @default.
- W2966705583 crossrefType "proceedings-article" @default.
- W2966705583 hasAuthorship W2966705583A5014641216 @default.
- W2966705583 hasAuthorship W2966705583A5042782010 @default.
- W2966705583 hasAuthorship W2966705583A5088843448 @default.
- W2966705583 hasBestOaLocation W29667055831 @default.
- W2966705583 hasConcept C101738243 @default.
- W2966705583 hasConcept C108583219 @default.
- W2966705583 hasConcept C119857082 @default.
- W2966705583 hasConcept C153083717 @default.
- W2966705583 hasConcept C153180895 @default.
- W2966705583 hasConcept C154945302 @default.
- W2966705583 hasConcept C41008148 @default.
- W2966705583 hasConcept C41608201 @default.
- W2966705583 hasConcept C50644808 @default.
- W2966705583 hasConcept C59404180 @default.
- W2966705583 hasConcept C70518039 @default.
- W2966705583 hasConcept C80444323 @default.
- W2966705583 hasConcept C95623464 @default.
- W2966705583 hasConcept C97931131 @default.
- W2966705583 hasConceptScore W2966705583C101738243 @default.
- W2966705583 hasConceptScore W2966705583C108583219 @default.
- W2966705583 hasConceptScore W2966705583C119857082 @default.
- W2966705583 hasConceptScore W2966705583C153083717 @default.
- W2966705583 hasConceptScore W2966705583C153180895 @default.
- W2966705583 hasConceptScore W2966705583C154945302 @default.
- W2966705583 hasConceptScore W2966705583C41008148 @default.
- W2966705583 hasConceptScore W2966705583C41608201 @default.
- W2966705583 hasConceptScore W2966705583C50644808 @default.
- W2966705583 hasConceptScore W2966705583C59404180 @default.
- W2966705583 hasConceptScore W2966705583C70518039 @default.
- W2966705583 hasConceptScore W2966705583C80444323 @default.
- W2966705583 hasConceptScore W2966705583C95623464 @default.
- W2966705583 hasConceptScore W2966705583C97931131 @default.
- W2966705583 hasLocation W29667055831 @default.
- W2966705583 hasOpenAccess W2966705583 @default.
- W2966705583 hasPrimaryLocation W29667055831 @default.
- W2966705583 hasRelatedWork W2467256294 @default.
- W2966705583 hasRelatedWork W2592385986 @default.
- W2966705583 hasRelatedWork W2959689543 @default.
- W2966705583 hasRelatedWork W2966705583 @default.
- W2966705583 hasRelatedWork W2998168123 @default.
- W2966705583 hasRelatedWork W3000441509 @default.
- W2966705583 hasRelatedWork W3165463024 @default.
- W2966705583 hasRelatedWork W4287178339 @default.
- W2966705583 hasRelatedWork W4287995534 @default.
- W2966705583 hasRelatedWork W4321789545 @default.
- W2966705583 isParatext "false" @default.
- W2966705583 isRetracted "false" @default.
- W2966705583 magId "2966705583" @default.
- W2966705583 workType "article" @default.