GNN-meta-attack-pytorch

Pytorch implementation of the paper Adversarial Attacks on Graph Neural Networks via Meta Learning.

Original implementation in Tensorflow by Daniel Zügner is available here. https://github.com/danielzuegner/gnn-meta-attack

Dependencies

1. Python 3.6+
2. Pytorch 1.0.1+
3. numpy
4. scipy

Run the code

sh run_attack.sh

Citation to the original paper

@inproceedings{zugner_adversarial_2019,
	title = {Adversarial Attacks on Graph Neural Networks via Meta Learning},
	author={Z{\"u}gner, Daniel and G{\"u}nnemann, Stephan},
	booktitle={International Conference on Learning Representations (ICLR)},
	year = {2019}
}