r""" Description ----------- Strategy to early stop attack process.

r""" Description ----------- RobustGCN convolutional layer. Parameters ---------- in_features : int Dimension of input

Adaptive Graph Injection Attacks with gradients

Efficient GCNGuard

r""" Node similarity regularized PGD on graphs

r""" Description ----------- Graph injection attack version of Projected Gradient Descent attack (`PGD <https://arxiv.org/abs/1706.06083>

Robust GAT inspired by GNNGuard

random edge connection, random feature generation

r""" Description ----------- Robust Graph Convolutional Networks (`RobustGCN <http://pengcui.thumedialab.com/papers/RGCN.pdf>`__) Para

r""" Graph Injection Attack in a Squential manner

r""" Description ----------- SPEIT graph injection attack, 1st place solution of KDD CUP 2020 Graph Adversarial Attack & Defense. (`S

Vanilla attack that does nothing