Home

Awesome

Position-aware Graph Neural Networks

This repository is the official PyTorch implementation of "Position-aware Graph Neural Networks".

Jiaxuan You, Rex Ying, Jure Leskovec, Position-aware Graph Neural Networks, ICML 2019 (long oral).

Installation

conda install pytorch torchvision cudatoolkit=9.0 -c pytorch
pip install --verbose --no-cache-dir torch-scatter
pip install --verbose --no-cache-dir torch-sparse
pip install --verbose --no-cache-dir torch-cluster
pip install --verbose --no-cache-dir torch-spline-conv (optional)
pip install torch-geometric
pip install networkx
pip install tensorboardX

Run

python main.py --model GCN --layer_num 3 --dataset grid
python main.py --model PGNN --layer_num 2 --dataset grid
python main.py --model GCN --layer_num 2 --approximate 2 --dataset grid
python main.py --model GCN --layer_num 3 --dataset All
python main.py --model PGNN --layer_num 2 --dataset All

You are highly encouraged to tune all kinds of hyper-parameters to get better performance. We only did very limited hyper-parameter tuning.

We recommend using tensorboard to monitor the training process. To do this, you may run

tensorboard --logdir runs