search

ChandlerBang / Pro-GNN

Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
https://arxiv.org/abs/2005.10203
285 stars 45 forks source link

About the attacked graph #14

Open Wangbeibei-AHU opened 3 years ago

Wangbeibei-AHU commented 3 years ago

Thanks for sharing the code. I'd like to ask you about the details of the attacked graph. I find that the perturbed_adj generated by mettack or nettack methods is symmetric. But when I get the perturbed_adj by conducting adversarial attack (meta and nettack) from deeprobust library, I find that it is asymmetric. What caused the difference in data? Did you preprocess the perturbed_adj? Looking forward to your reply.

ChandlerBang commented 3 years ago

Hi, thanks for your interest in our work.

Can you provide more details on this issue? The deeprobust library should generate symmetric graphs.