BriefGPT.xyz
Jul, 2020
简单而深入的图卷积网络
Simple and Deep Graph Convolutional Networks
HTML
PDF
Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li
TL;DR
本研究提出了一种使用深度学习解决图像识别问题的方法——GCNII，并通过两种新技术—初始残差和身份映射—缓解了问题过度平滑的问题。实验结果表明深度GCNII模型在半监督和全监督任务中的性能优于现有方法。
Abstract
graph convolutional networks
(GCNs) are a powerful
deep learning
approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-wor
→