Wei Jin

Hi, Thank you for your feedback. 1. We follow the author's implementation to normalize the feature matrix. (see https://github.com/KaidiXu/GCN_ADV_Train/blob/master/train.py) 2/3. Are you using the latest code? The latest code should...

> Thanks for your reply. I find the reason anyway. The func-def preprocess is not the same in github/DeepRobust/utils.py as it in the Lib. I reinstall deeprobust-0.2.4, but it still...

> Is there any difference between these two dataloaders? Pyg dataloader provides fixed data splits and full graph as in the original GCN paper; `gcn` provides randomly selected splits with...

nettack是targeted attack，会对target node影响很大，但对模型整体效果影响不大。 你可以看看这个文件[test_nettack.py](https://github.com/DSE-MSU/DeepRobust/blob/master/examples/graph/test_nettack.py).

> I believe all of the segfaults are caused by building with an older version of gcc. I'm using a conda environment and did `conda install gcc_linux-64 gxx_linux-64` and reinstalled...

Hi, currently we do not have the plan to implement that for graph classification. We may include that in the future. Thanks.

Hi, The current code does not support attacking GAT using the topology attack. You may refer to the [PRBCD attack](https://github.com/sigeisler/robustness_of_gnns_at_scale/blob/main/rgnn_at_scale/attacks/prbcd.py#L128) to implement the attack with PyG. However, we will soon...

Hey, you may take a look at [their paper](https://arxiv.org/abs/2110.14038) first. Basically, at each step they will sample a block of edge indices (a small portion of all the possible edge...

> Hi! Thanks for sharing the code, I'd like to ask you about the details of the datasets! for the Citeseer dataset, the edges of LCC in your article are...

> > Basically, we just sequentially attack those target nodes. I modified the [example code](https://github.com/DSE-MSU/DeepRobust/blob/master/examples/graph/test_nettack.py) as follows > > ``` > > from deeprobust.graph.defense import GCN > > from deeprobust.graph.targeted_attack...