DII-GCN: Dropedge Based Deep Graph Convolutional Networks
Graph neural networks (GNNs) have gradually become an important research branch in graph learning since 2005, and the most active one is unquestionably graph convolutional neural networks (GCNs). Although convolutional neural networks have successfully learned for images, voices, and texts, over-smo...
Main Authors: | Jinde Zhu, Guojun Mao, Chunmao Jiang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/14/4/798 |
Similar Items
-
ABCDE: Approximating Betweenness-Centrality ranking with progressive-DropEdge
by: Martin Mirakyan
Published: (2021-09-01) -
DEJKMDR: miRNA-disease association prediction method based on graph convolutional network
by: Shiyuan Gao, et al.
Published: (2023-09-01) -
Review of Text Classification Methods Based on Graph Convolutional Network
by: TAN Ying-ying, WANG Jun-li, ZHANG Chao-bo
Published: (2022-08-01) -
Limits of Depth: Over-Smoothing and Over-Squashing in GNNs
by: Aafaq Mohi ud din, et al.
Published: (2024-03-01) -
Interest-Aware Message-Passing Layer-Refined Graph Convolutional Network for Recommendation
by: Xingyao Yang, et al.
Published: (2023-05-01)