Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213302843> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3213302843 endingPage "9044" @default.
- W3213302843 startingPage "9033" @default.
- W3213302843 abstract "Abstract A graph can represent a complex organization of data in which dependencies exist between multiple entities or activities. Such complex structures create challenges for machine learning algorithms, particularly when combined with the high dimensionality of data in current applications. Graph convolutional networks were introduced to adopt concepts from deep convolutional networks (i.e. the convolutional operations/layers) that have shown good results. In this context, we propose two major enhancements to two of the existing graph convolutional network frameworks: (1) topological information enrichment through clustering coefficients; and (2) structural redesign of the network through the addition of dense layers. Furthermore, we propose minor enhancements using convex combinations of activation functions and hyper-parameter optimization. We present extensive results on four state-of-art benchmark datasets. We show that our approach achieves competitive results for three of the datasets and state-of-the-art results for the fourth dataset while having lower computational costs compared to competing methods." @default.
- W3213302843 created "2021-11-22" @default.
- W3213302843 creator A5006608063 @default.
- W3213302843 creator A5010571416 @default.
- W3213302843 creator A5011670526 @default.
- W3213302843 creator A5012061595 @default.
- W3213302843 date "2021-11-16" @default.
- W3213302843 modified "2023-10-02" @default.
- W3213302843 title "Graph convolutional networks: analysis, improvements and results" @default.
- W3213302843 cites W1970463918 @default.
- W3213302843 cites W2003456502 @default.
- W3213302843 cites W2051436535 @default.
- W3213302843 cites W2116341502 @default.
- W3213302843 cites W2407712691 @default.
- W3213302843 cites W2600702321 @default.
- W3213302843 cites W2786627679 @default.
- W3213302843 cites W2797716674 @default.
- W3213302843 cites W2962730440 @default.
- W3213302843 cites W2998496395 @default.
- W3213302843 cites W3101398262 @default.
- W3213302843 cites W3104097132 @default.
- W3213302843 cites W3105136071 @default.
- W3213302843 cites W80183829 @default.
- W3213302843 doi "https://doi.org/10.1007/s10489-021-02973-4" @default.
- W3213302843 hasPublicationYear "2021" @default.
- W3213302843 type Work @default.
- W3213302843 sameAs 3213302843 @default.
- W3213302843 citedByCount "12" @default.
- W3213302843 countsByYear W32133028432022 @default.
- W3213302843 countsByYear W32133028432023 @default.
- W3213302843 crossrefType "journal-article" @default.
- W3213302843 hasAuthorship W3213302843A5006608063 @default.
- W3213302843 hasAuthorship W3213302843A5010571416 @default.
- W3213302843 hasAuthorship W3213302843A5011670526 @default.
- W3213302843 hasAuthorship W3213302843A5012061595 @default.
- W3213302843 hasBestOaLocation W32133028431 @default.
- W3213302843 hasConcept C106937863 @default.
- W3213302843 hasConcept C111030470 @default.
- W3213302843 hasConcept C119857082 @default.
- W3213302843 hasConcept C124101348 @default.
- W3213302843 hasConcept C132525143 @default.
- W3213302843 hasConcept C13280743 @default.
- W3213302843 hasConcept C154945302 @default.
- W3213302843 hasConcept C185798385 @default.
- W3213302843 hasConcept C205649164 @default.
- W3213302843 hasConcept C41008148 @default.
- W3213302843 hasConcept C73555534 @default.
- W3213302843 hasConcept C80444323 @default.
- W3213302843 hasConcept C81363708 @default.
- W3213302843 hasConceptScore W3213302843C106937863 @default.
- W3213302843 hasConceptScore W3213302843C111030470 @default.
- W3213302843 hasConceptScore W3213302843C119857082 @default.
- W3213302843 hasConceptScore W3213302843C124101348 @default.
- W3213302843 hasConceptScore W3213302843C132525143 @default.
- W3213302843 hasConceptScore W3213302843C13280743 @default.
- W3213302843 hasConceptScore W3213302843C154945302 @default.
- W3213302843 hasConceptScore W3213302843C185798385 @default.
- W3213302843 hasConceptScore W3213302843C205649164 @default.
- W3213302843 hasConceptScore W3213302843C41008148 @default.
- W3213302843 hasConceptScore W3213302843C73555534 @default.
- W3213302843 hasConceptScore W3213302843C80444323 @default.
- W3213302843 hasConceptScore W3213302843C81363708 @default.
- W3213302843 hasFunder F4320335254 @default.
- W3213302843 hasIssue "8" @default.
- W3213302843 hasLocation W32133028431 @default.
- W3213302843 hasLocation W32133028432 @default.
- W3213302843 hasOpenAccess W3213302843 @default.
- W3213302843 hasPrimaryLocation W32133028431 @default.
- W3213302843 hasRelatedWork W112744582 @default.
- W3213302843 hasRelatedWork W1485630101 @default.
- W3213302843 hasRelatedWork W1509595664 @default.
- W3213302843 hasRelatedWork W2498017833 @default.
- W3213302843 hasRelatedWork W2748454020 @default.
- W3213302843 hasRelatedWork W2961085424 @default.
- W3213302843 hasRelatedWork W3021430260 @default.
- W3213302843 hasRelatedWork W3027997911 @default.
- W3213302843 hasRelatedWork W4287776258 @default.
- W3213302843 hasRelatedWork W4380482045 @default.
- W3213302843 hasVolume "52" @default.
- W3213302843 isParatext "false" @default.
- W3213302843 isRetracted "false" @default.
- W3213302843 magId "3213302843" @default.
- W3213302843 workType "article" @default.