Matches in SemOpenAlex for { <https://semopenalex.org/work/W2916446912> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2916446912 abstract "We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with an optimization process. Extensive experiments on three citation network datasets Cora, Citeseer and Pubmed and a knowledge graph dataset Nell validate the effectiveness of the proposed method, which establishes state-of-the-art results in the semi-supervised node classification tasks." @default.
- W2916446912 created "2019-03-02" @default.
- W2916446912 creator A5003713785 @default.
- W2916446912 creator A5065011438 @default.
- W2916446912 creator A5068755794 @default.
- W2916446912 date "2019-02-25" @default.
- W2916446912 modified "2023-10-14" @default.
- W2916446912 title "Batch Virtual Adversarial Training for Graph Convolutional Networks" @default.
- W2916446912 cites W2104290444 @default.
- W2916446912 cites W2139823104 @default.
- W2916446912 cites W2145494108 @default.
- W2916446912 cites W2152722485 @default.
- W2916446912 cites W2153959628 @default.
- W2916446912 cites W2407712691 @default.
- W2916446912 cites W2558460151 @default.
- W2916446912 cites W2592691248 @default.
- W2916446912 cites W2624431344 @default.
- W2916446912 cites W2753542656 @default.
- W2916446912 cites W2767045141 @default.
- W2916446912 cites W2773131141 @default.
- W2916446912 cites W2790814121 @default.
- W2916446912 cites W2803678876 @default.
- W2916446912 cites W2962756421 @default.
- W2916446912 cites W2962767366 @default.
- W2916446912 cites W2963207607 @default.
- W2916446912 cites W2963312446 @default.
- W2916446912 cites W2963435192 @default.
- W2916446912 cites W2963558289 @default.
- W2916446912 cites W2963857521 @default.
- W2916446912 cites W2964015378 @default.
- W2916446912 cites W2964121744 @default.
- W2916446912 cites W2964159205 @default.
- W2916446912 cites W2964321699 @default.
- W2916446912 cites W3093419064 @default.
- W2916446912 cites W3104097132 @default.
- W2916446912 cites W92894758 @default.
- W2916446912 doi "https://doi.org/10.48550/arxiv.1902.09192" @default.
- W2916446912 hasPublicationYear "2019" @default.
- W2916446912 type Work @default.
- W2916446912 sameAs 2916446912 @default.
- W2916446912 citedByCount "27" @default.
- W2916446912 countsByYear W29164469122019 @default.
- W2916446912 countsByYear W29164469122020 @default.
- W2916446912 countsByYear W29164469122021 @default.
- W2916446912 countsByYear W29164469122022 @default.
- W2916446912 crossrefType "posted-content" @default.
- W2916446912 hasAuthorship W2916446912A5003713785 @default.
- W2916446912 hasAuthorship W2916446912A5065011438 @default.
- W2916446912 hasAuthorship W2916446912A5068755794 @default.
- W2916446912 hasBestOaLocation W29164469121 @default.
- W2916446912 hasConcept C119857082 @default.
- W2916446912 hasConcept C124101348 @default.
- W2916446912 hasConcept C127413603 @default.
- W2916446912 hasConcept C132525143 @default.
- W2916446912 hasConcept C154945302 @default.
- W2916446912 hasConcept C2776135515 @default.
- W2916446912 hasConcept C37736160 @default.
- W2916446912 hasConcept C41008148 @default.
- W2916446912 hasConcept C62611344 @default.
- W2916446912 hasConcept C66938386 @default.
- W2916446912 hasConcept C80444323 @default.
- W2916446912 hasConceptScore W2916446912C119857082 @default.
- W2916446912 hasConceptScore W2916446912C124101348 @default.
- W2916446912 hasConceptScore W2916446912C127413603 @default.
- W2916446912 hasConceptScore W2916446912C132525143 @default.
- W2916446912 hasConceptScore W2916446912C154945302 @default.
- W2916446912 hasConceptScore W2916446912C2776135515 @default.
- W2916446912 hasConceptScore W2916446912C37736160 @default.
- W2916446912 hasConceptScore W2916446912C41008148 @default.
- W2916446912 hasConceptScore W2916446912C62611344 @default.
- W2916446912 hasConceptScore W2916446912C66938386 @default.
- W2916446912 hasConceptScore W2916446912C80444323 @default.
- W2916446912 hasLocation W29164469121 @default.
- W2916446912 hasOpenAccess W2916446912 @default.
- W2916446912 hasPrimaryLocation W29164469121 @default.
- W2916446912 hasRelatedWork W2945796017 @default.
- W2916446912 hasRelatedWork W2953770707 @default.
- W2916446912 hasRelatedWork W2964583308 @default.
- W2916446912 hasRelatedWork W3034334914 @default.
- W2916446912 hasRelatedWork W3168561516 @default.
- W2916446912 hasRelatedWork W3196755225 @default.
- W2916446912 hasRelatedWork W4288293779 @default.
- W2916446912 hasRelatedWork W4302283439 @default.
- W2916446912 hasRelatedWork W4319453562 @default.
- W2916446912 hasRelatedWork W4323323198 @default.
- W2916446912 isParatext "false" @default.
- W2916446912 isRetracted "false" @default.
- W2916446912 magId "2916446912" @default.
- W2916446912 workType "article" @default.