Deep graph learning for semi-supervised classification

作者：

Highlights：

• The global and local structure are jointly considered for deep graph learning networks.

• The relationship of the structures are mined by the hierarchical progressive learning.

• The different structures fusion are dynamically encoded by their interdependence.

摘要

•The global and local structure are jointly considered for deep graph learning networks.•The relationship of the structures are mined by the hierarchical progressive learning.•The different structures fusion are dynamically encoded by their interdependence.

论文关键词：Graph learning,Graph convolutional networks,Semi-supervised classification

论文评审过程：Received 17 June 2020, Revised 19 March 2021, Accepted 10 May 2021, Available online 19 May 2021, Version of Record 28 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108039