Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective

no code implementations • 24 Sep 2020 • Hongwei Zhang, Tijin Yan, Zenjun Xie, Yuanqing Xia, Yuan Zhang

Based on our theoretical and empirical analysis, we establish a universal theoretical framework of GCN from an optimization perspective and derive a novel convolutional kernel named GCN+ which has lower parameter amount while relieving the over-smoothing inherently.

General Classification Node Classification