Node classification using kernel propagation in graph neural networks

作者：

Highlights：

• Spectral Kernel propagation layer for differentiating local/global connectivity.

• Multiplicative attention mechanism that improves the stability of learning.

• Node classification without the use of additional node attributes/features.

摘要

•Spectral Kernel propagation layer for differentiating local/global connectivity.•Multiplicative attention mechanism that improves the stability of learning.•Node classification without the use of additional node attributes/features.

论文关键词：Deep learning,Node classification,Network embedding,Graph neural networks,Attention

论文评审过程：Received 27 March 2020, Revised 23 January 2021, Accepted 23 January 2021, Available online 4 February 2021, Version of Record 11 March 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114655