用於支援論文《Relational inductive biases, deep learning, and graph networks》。

github

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).

講直白一些，就是用神經網路處理圖，輸入是圖，輸出也是圖。以前都是處理向量(Vector)，所以NLP中需要做Word2Vec後才能運用深度學習的處理結果。作者們認為 Graph2Graph 是讓神經網路具備推理(Reason)能力的一個關鍵步驟。

【CNN已老，GNN來了】DeepMind、谷歌大腦、MIT等27位作者重磅論文，圖網路讓深度學習也能因果推理