本文主要是介绍最早提出“基于时空的图神经网络”论文:Learning Convolutional Neural Networks for Graphs 阅读笔记,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!
卷积过程:
将卷积过程迁移到图卷积中需要考虑两个问题:
(i) Determining the node sequences for which neighborhood graphs are created;决定围绕哪些结点创建邻接图(比如上图1中的结点1-4)
(ii) computing a normalization of neighborhood graphs, that is, a unique mapping from a graph representation into a vector space representation.得到图的表示之后,如何向量化
这篇关于最早提出“基于时空的图神经网络”论文:Learning Convolutional Neural Networks for Graphs 阅读笔记的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!