graphSAGE/Inductive Representation Learning on Large Graphs
文章目录总结细节实验总结通过邻居节点,计算节点emb,可以无监督学习细节对于unseen的节点也能产出emb,主要是通过对邻居节点的学习计算节点emb的算法步骤节点emb初始化计算节点v的邻居节点emb:hN(v)k←AGGREGATEk({huk−1,∀u∈N(v)})h_{\mathcal{N}(v)}^k\leftarrow\text{AGGREGATE}_k(\{h_u^{k-1},\fo