Train GCN and MLP for all datasets.

Train GCN:

python3 train.py --dataset cora --model gcn

Train MLP:

python3 train.py --dataset cora --model mlp

Split train / test for all datasets.

Add partial_graph_with_id folder under data.

python3 partial_graph_generation.py --dataset cora

Note that all attacks rely on the partial graphs generated by Step 2.

python3 attack.py --dataset cora

chmod 775 run_exp.sh then ./run_exp.sh dataset

This is a Pytorch implementation of Stealing links from Graph Neural Networks from github.