This is the code for paper
Ubuntu16.04 + NVIDIA-1080TI
Anaconda + python 3.7
numpy==1.19.4
scipy==1.5.4
ogb==1.2.3
texttable==1.6.3
torch==1.6.0+cu101
torchvision==0.7.0+cu101
torch-cluster==1.5.8
torch-geometric==1.6.1
torch-scatter==2.0.5
torch-sparse==0.6.8
torch-spline-conv==1.2.0
run R-GSN
python rgsn.py --device $Device --conv_name "rgsn"\
--test_batch_size 64 \
--Norm4 True \
--FDFT True \
--use_attack True
run baseline R-GCN
python rgsn.py --device $Device --conv_name "rgcn"
model | params | valid | test |
---|---|---|---|
R-GCN | 154,366,772 | 47.61±0.68 | 46.78±0.67 |
R-GSN | 154,373,028 | 51.82±0.41 | 50.32±0.37 |