Wei Jin

Hi, Nettack can only deal with **binary and sparse features/structure** perturbation but in ogbn-arxiv the features are continuous and dense. That is why it fails. You may want to set...

Hi, what do you mean by"does not match this code"? Just install the latest version of deeprobust and clone this repository; everything should be good. Let me know if you...

这个device可以接收torch.device也可以接收string，所以没什么问题的。 至于你说其他的报错，你可以把error贴出来看看。

Can you provide more details on this bug? Did you tried `examples/test_mettatck.py`?

Hi, I just tried `examples/test_mettack.py` with `torch==1.10.0` and it works fine for me. Can you provide more details on the error information? (by copying the whole error message)

Ok, let me see if I can figure it out.

I am not sure about the detailed gpu memory usage for attacking pubmed but I made it on a GPU with 32GB. The memory complexity of metattack is very high...

Hi, thanks for your interest in our work. Can you provide more details on this issue? The deeprobust library should generate symmetric graphs.

Hi, Thanks for your interest in our work. The 186 targeted nodes are already sampled so you don't need to sample from them again. According to our paper, > The...

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 import Nettack from deeprobust.graph.utils import * from deeprobust.graph.data...