摘要 : GCN is a widely-used representation learning method for capturing hidden features in graph data. However, traditional GCNs suffer from the over-smoothing problem, hindering their ability to extract high-order information and obtai... 展开
作者 | He~ Liancheng Bai~ Liang Yang~ Xian Du~ Hangyuan Liang~ Jiye |
---|---|
作者单位 | |
期刊名称 | 《Information Sciences: An International Journal》 |
总页数 | 13 |
语种/中图分类号 | 英语 / TP14 TP39 G2 TP |
关键词 | Graph neural network Graph convolutional network Attention mechanism High-order information REGULARIZATION |
馆藏号 | N2008EPST0000863 |