DeepMind 开源图神经网络的代码

用于支持论文《Relational inductive biases, deep learning, and graph networks》。node

githubgit

A graph network takes a graph as input and returns a graph as output. The input graph has edge- (E ), node- (V ), and global-level (u) attributes. The output graph has the same structure, but updated attributes. Graph networks are part of the broader family of "graph neural networks" (Scarselli et al., 2009).github

讲直白一些,就是用神经网络处理图,输入是图,输出也是图。之前都是处理向量(Vector),因此NLP中须要作Word2Vec后才能运用深度学习的处理结果。做者们认为 Graph2Graph 是让神经网络具有推理(Reason)能力的一个关键步骤。网络

【CNN已老,GNN来了】DeepMind、谷歌大脑、MIT等27位做者重磅论文,图网络让深度学习也能因果推理学习

相关文章
相关标签/搜索