Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287816705> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4287816705 abstract "Graph convolutional neural networks (GCNNs) are a powerful extension of deep learning techniques to graph-structured data problems. We empirically evaluate several pooling methods for GCNNs, and combinations of those graph pooling methods with three different architectures: GCN, TAGCN, and GraphSAGE. We confirm that graph pooling, especially DiffPool, improves classification accuracy on popular graph classification datasets and find that, on average, TAGCN achieves comparable or better accuracy than GCN and GraphSAGE, particularly for datasets with larger and sparser graph structures." @default.
- W4287816705 created "2022-07-26" @default.
- W4287816705 creator A5001259459 @default.
- W4287816705 creator A5045374702 @default.
- W4287816705 creator A5045861415 @default.
- W4287816705 creator A5070638493 @default.
- W4287816705 creator A5085004466 @default.
- W4287816705 date "2020-04-07" @default.
- W4287816705 modified "2023-09-28" @default.
- W4287816705 title "Pooling in Graph Convolutional Neural Networks" @default.
- W4287816705 doi "https://doi.org/10.48550/arxiv.2004.03519" @default.
- W4287816705 hasPublicationYear "2020" @default.
- W4287816705 type Work @default.
- W4287816705 citedByCount "0" @default.
- W4287816705 crossrefType "posted-content" @default.
- W4287816705 hasAuthorship W4287816705A5001259459 @default.
- W4287816705 hasAuthorship W4287816705A5045374702 @default.
- W4287816705 hasAuthorship W4287816705A5045861415 @default.
- W4287816705 hasAuthorship W4287816705A5070638493 @default.
- W4287816705 hasAuthorship W4287816705A5085004466 @default.
- W4287816705 hasBestOaLocation W42878167051 @default.
- W4287816705 hasConcept C119857082 @default.
- W4287816705 hasConcept C132525143 @default.
- W4287816705 hasConcept C153180895 @default.
- W4287816705 hasConcept C154945302 @default.
- W4287816705 hasConcept C41008148 @default.
- W4287816705 hasConcept C70437156 @default.
- W4287816705 hasConcept C80444323 @default.
- W4287816705 hasConcept C81363708 @default.
- W4287816705 hasConceptScore W4287816705C119857082 @default.
- W4287816705 hasConceptScore W4287816705C132525143 @default.
- W4287816705 hasConceptScore W4287816705C153180895 @default.
- W4287816705 hasConceptScore W4287816705C154945302 @default.
- W4287816705 hasConceptScore W4287816705C41008148 @default.
- W4287816705 hasConceptScore W4287816705C70437156 @default.
- W4287816705 hasConceptScore W4287816705C80444323 @default.
- W4287816705 hasConceptScore W4287816705C81363708 @default.
- W4287816705 hasLocation W42878167051 @default.
- W4287816705 hasOpenAccess W4287816705 @default.
- W4287816705 hasPrimaryLocation W42878167051 @default.
- W4287816705 hasRelatedWork W11594795 @default.
- W4287816705 hasRelatedWork W12336802 @default.
- W4287816705 hasRelatedWork W12793662 @default.
- W4287816705 hasRelatedWork W13824394 @default.
- W4287816705 hasRelatedWork W3281095 @default.
- W4287816705 hasRelatedWork W3979659 @default.
- W4287816705 hasRelatedWork W6581905 @default.
- W4287816705 hasRelatedWork W7303821 @default.
- W4287816705 hasRelatedWork W9043603 @default.
- W4287816705 hasRelatedWork W9190101 @default.
- W4287816705 isParatext "false" @default.
- W4287816705 isRetracted "false" @default.
- W4287816705 workType "article" @default.