Questions about node selection in Nettack

[Leirunlin]

Hi! Thanks for sharing the code. I have a question about the selection of target nodes in Nettack. I notice that in test_nettack.py, about 40 nodes are chosen as the target nodes following the original paper. In Pro-GNN, nodes in the test set whose degrees are larger than 10 are chosen. Did I misunderstand the experiment settings?

[ChandlerBang]

Hey, you understanding it correct. ProGNN follows RGCN to select nodes in the test set whose degrees are larger than 10 and these target nodes are attacked to form one new graph. Please run scripts to see more details.

The setting in test_nettack.py is difference and it is exactly the setting in the original nettack paper.

[Leirunlin]

Thanks! I was confused before by the reply in issue #12 . You only mentioned changes in the sequential attack in test.py, but not the changes in node selection. It would be really helpful for people who want to conduct their own attacks for comparison if the experiment setting is clarified. I think an example about Nettack would be even better like there is a "generate_attack.py" about Metattack. But anyway, it is so nice of you to give such a quick and detailed reply!