Hardware environment: Intel(R) Xeon(R) Gold 6230R CPU @ 2.10GHz, NVIDIA GeForce RTX 3090 with 24GB memory.
Software environment: Ubuntu 18.04.6, Python 3.9, PyTorch 1.11.0 and CUDA 11.8.
- Please refer to PyTorch and PyG to install the environments;
- Run 'pip install -r requirements.txt' to download required packages;
To train the model(s) in the paper
- Please put the data under the dataset/homo_data, we have already downloaded cora as examples.
- Open main.py to run our program with our ATP plug-in. We need to generate
degree_centrality
,clustering_coefficients
,Engienvector_centrality
.
for example, if you want to run cora under sgc model, just try the command below
python main.py --prop_steps 10 --model_name sgc --data_name cora --r_way together --lr 0.2 --dropout 0.0 --weight_decay 1e-5 --num_epochs 150 --a 0.3 --b 0.7 --c 0.0 --normalize_times 10 --gpu_id 1