Graph Neural Networks: Architectures, Stability and Transferability
Proceedings of the IEEE(2021)
摘要
Graph neural networks (GNNs) are information processing architectures for signals supported on graphs. They are presented here as generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph convolutional filters instead of banks of classical convolutional filters. Otherwise, GNNs operate as CNNs. Filters are composed of pointwise nonlinearities and sta...
更多查看译文
关键词
Training,Stability analysis,Convolution,Neural networks,Transforms,Strain,Probability distribution
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要