DeepGCNs: Can GCNs Go as Deep as CNNs?
GPTKB entity
Statements (20)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:academic_journal
|
| gptkbp:address |
over-smoothing in deep GCNs
|
| gptkbp:author |
gptkb:Matthias_Müller
gptkb:Bernard_Ghanem gptkb:Guohao_Li Ali Thabet |
| gptkbp:citation |
1000+
|
| gptkbp:field |
deep learning
graph neural networks |
| gptkbp:focusesOn |
training very deep graph convolutional networks
|
| gptkbp:proposedBy |
DeepGCN architecture
|
| gptkbp:publicationYear |
2019
|
| gptkbp:publishedIn |
gptkb:ICCV_2019
|
| gptkbp:url |
https://arxiv.org/abs/1904.03751
|
| gptkbp:uses |
dilated convolutions
residual connections dense connections |
| gptkbp:bfsParent |
gptkb:ResGCN
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
DeepGCNs: Can GCNs Go as Deep as CNNs?
|