Question about deriving Eq.(17) about nettack

[danielzuegner]

Hi,

Thanks for your interest in our work. I'm not sure I understand the question, so I'll just give the answer a shot. Feel free to ask a follow-up question if anything remains unclear.

It seems that you're confused about A, A_tilde, and A_hat in the proof of Eq. (17). Specifically, the confusion seems to be about the first full-row equation in the proof [A_hat_square]_{uv} = …. The difference between A_tilde and A is subtle. As specified right below Eq. (1), A_tilde is the adjacency matrix with added self-loops (via adding the identity matrix). A_hat, on the other hand, is the degree-normalized version of A_tilde (see below Eq. (2)).

In the proof we use at several places the fact that diagonal elements A_{uu}=0 as we consider graphs without self-loops, while A_tilde_{uu}=1 because we added the self-loops.

[ThatDanielLiu]

Oh thanks for the detailed explanation, I totally get it.