Training Matters: Unlocking Potentials of Deeper Graph Convolutional
Neural Networks

Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks

20 August 2020

Sitao Luan

Papers citing "Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks"

5 / 5 papers shown

Title
Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again Ajay Jaiswal Peihao Wang Tianlong Chen Justin F. Rousseau Ying Ding Zhangyang Wang 32 10 0 14 Oct 2022
Revisiting Heterophily For Graph Neural Networks Sitao Luan Chenqing Hua Qincheng Lu Jiaqi Zhu Mingde Zhao Shuyuan Zhang Xiaoming Chang Doina Precup 41 179 0 14 Oct 2022
On Provable Benefits of Depth in Training Graph Convolutional Networks Weilin Cong M. Ramezani M. Mahdavi 24 73 0 28 Oct 2021
Geometric deep learning on graphs and manifolds using mixture model CNNs Federico Monti Davide Boscaini Jonathan Masci Emanuele Rodolà Jan Svoboda M. Bronstein GNN 251 1,811 0 25 Nov 2016
Geometric deep learning: going beyond Euclidean data M. Bronstein Joan Bruna Yann LeCun Arthur Szlam P. Vandergheynst GNN 253 3,239 0 24 Nov 2016