Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again

Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again

14 October 2022

Justin F. Rousseau

Papers citing "Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again"

12 / 12 papers shown

Title
Enhanced Soups for Graph Neural Networks Joseph Zuber Aishwarya Sarkar Joseph Jennings Ali Jannesari 45 0 0 14 Mar 2025
Reducing Oversmoothing through Informed Weight Initialization in Graph Neural Networks Dimitrios Kelesis Dimitris Fotakis G. Paliouras 21 0 0 31 Oct 2024
Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks Jie Peng Runlin Lei Zhewei Wei 18 4 0 07 Aug 2024
On the Initialization of Graph Neural Networks Jiahang Li Ya-Zhi Song Xiang Song David Wipf GNN 8 5 0 05 Dec 2023
Are GATs Out of Balance? Nimrah Mustafa Aleksandar Bojchevski R. Burkholz 41 4 0 11 Oct 2023
Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations G. Dezoort Boris Hanin AI4CE 15 3 0 20 Jun 2023
Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication A. Jaiswal Shiwei Liu Tianlong Chen Ying Ding Zhangyang Wang GNN 31 5 0 18 Jun 2023
SoGCN: Second-Order Graph Convolutional Networks Peihao Wang Yuehao Wang Hua Lin Jianbo Shi 11 3 0 14 Oct 2021
L $^2$ -GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks Yuning You Tianlong Chen Zhangyang Wang Yang Shen GNN 86 82 0 30 Mar 2020
Geom-GCN: Geometric Graph Convolutional Networks Hongbin Pei Bingzhen Wei Kevin Chen-Chuan Chang Yu Lei Bo Yang GNN 167 1,058 0 13 Feb 2020
Representation Learning on Graphs with Jumping Knowledge Networks Keyulu Xu Chengtao Li Yonglong Tian Tomohiro Sonobe Ken-ichi Kawarabayashi Stefanie Jegelka GNN 229 1,935 0 09 Jun 2018
Densely Connected Convolutional Networks Gao Huang Zhuang Liu L. V. D. van der Maaten Kilian Q. Weinberger PINN 3DV 244 35,884 0 25 Aug 2016