GreatX
GreatX copied to clipboard
A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).
Hi. I have tried to run the [metattack.py](https://github.com/EdisonLeeeee/GreatX/blob/master/examples/attack/untargeted/metattack.py) file. But got this error. ``` TypeError: fit() got an unexpected keyword argument 'mask' ```
Ref: + [Robustness of Graph Neural Networks at Scale](https://www.cs.cit.tum.de/daml/robustness-of-gnns-at-scale) + https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/contrib/nn/models/rbcd_attack.py
Hi! Thanks for this great repo. I have some questions about the implementation of PGDAttack. 1) The learning rate of PGDAttack. https://github.com/EdisonLeeeee/GreatX/blob/49675e30ed38b2518f7a1b85b667de5f4a0c9a7c/greatx/attack/untargeted/pgd_attack.py#L42 In the original paper of PGDAttack and implementation...