Thanks for your work!
On your paper, you say "Overall, the computation procedures of these node embedding
methods can be divided into two stages: network augmentation
and embedding training", But I have read papers of Node Embedding and Knowledge Graph Embedding.
And I can't see that they all use network augmentation, whether is network augmentation just your own ideas before embedding training? Or whether you provide me material to prove that "Overall, the computation procedures of these node embedding
methods can be divided into two stages: network augmentation
and embedding training"