Are Graph Convolutional Networks With Random Weights Feasible?
Graph Convolutional Networks (GCNs), as a prominent example of graph neural networks, are receiving extensive attention for their powerful capability in learning node representations on graphs. There are various extensions, either in sampling and/or node feature aggregation, to further improve GCNs&...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 3 vom: 14. März, Seite 2751-2768
|
|---|
| 1. Verfasser: |
Huang, Changqin
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Li, Ming,
Cao, Feilong,
Fujita, Hamido,
Li, Zhao,
Wu, Xindong |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|