Co-embedding of edges and nodes with deep graph convolutional neural networks
Abstract Graph neural networks (GNNs) have significant advantages in dealing with non-Euclidean data and have been widely used in various fields. However, most of the existing GNN models face two main challenges: (1) Most GNN models built upon the message-passing framework exhibit a shallow structur...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Artigo |
| Sprache: | Inglês |
| Veröffentlicht: |
Nature Portfolio
2023-10-01
|
| Schriftenreihe: | Scientific Reports |
| Online-Zugang: | https://doi.org/10.1038/s41598-023-44224-1 |
| Tags: |
Keine Tags, Fügen Sie das erste Tag hinzu!
|