Co-embedding of edges and nodes with deep graph convolutional neural networks

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 structure, which...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhou, Yuchen, Huo, Hongtao, Hou, Zhiwen, Bu, Lingbin, Mao, Jingyi, Wang, Yifan, Lv, Xiaojun, Bu, Fanliang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10560674/
https://www.ncbi.nlm.nih.gov/pubmed/37807013
http://dx.doi.org/10.1038/s41598-023-44224-1

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10560674/
https://www.ncbi.nlm.nih.gov/pubmed/37807013
http://dx.doi.org/10.1038/s41598-023-44224-1

Ejemplares similares