Hybrid Low-Order and Higher-Order Graph Convolutional Networks

With the higher-order neighborhood information of a graph network, the accuracy of graph representation learning classification can be significantly improved. However, the current higher-order graph convolutional networks have a large number of parameters and high computational complexity. Therefore...

Descripción completa

Detalles Bibliográficos
Autores principales: Lei, Fangyuan, Liu, Xun, Dai, Qingyun, Ling, Bingo Wing-Kuen, Zhao, Huimin, Liu, Yan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2020
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7336866/
https://www.ncbi.nlm.nih.gov/pubmed/32788918
http://dx.doi.org/10.1155/2020/3283890

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7336866/
https://www.ncbi.nlm.nih.gov/pubmed/32788918
http://dx.doi.org/10.1155/2020/3283890

Ejemplares similares