Cargando…
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...
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: | |
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 |
Ejemplares similares
-
Semi-Supervised Multi-View Clustering with Weighted Anchor Graph Embedding
por: Wang, Senhong, et al.
Publicado: (2021) -
Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
por: KC, Kishan, et al.
Publicado: (2022) -
Graph embedding-based novel protein interaction prediction via higher-order graph convolutional network
por: Xiao, Ze, et al.
Publicado: (2020) -
Direct Estimation of Sizes of Higher-Order Graphs
por: Collins, J C, et al.
Publicado: (1997) -
HyperGraphs.jl: representing higher-order relationships in Julia
por: Diaz, Léo P M, et al.
Publicado: (2022)