A PyTorch implementation of DGCNN based on AAAI 2018 paper An End-to-End Deep Learning Architecture for Graph Classification.

• Anaconda
• PyTorch

conda install pytorch torchvision -c pytorch

• PyTorchNet

pip install git+https://github.com/pytorch/tnt.git@master

• PyTorch Geometric

pip install torch-scatter
pip install torch-sparse
pip install torch-cluster
pip install torch-spline-conv (optional)
pip install torch-geometric

The datasets are collected from graph kernel datasets. The code will download and extract them into data directory automatically. The 10fold_idx files are collected from pytorch_DGCNN.

python -m visdom.server -logging_level WARNING & python train.py --data_type PTC_MR --num_epochs 200
optional arguments:
--data_type dataset type [default value is 'DD'](choices:['DD', 'PTC_MR', 'NCI1', 'PROTEINS', 'IMDB-BINARY', 'IMDB-MULTI', 'MUTAG', 'COLLAB'])
--batch_size train batch size [default value is 50]
--num_epochs train epochs number [default value is 100]

Visdom now can be accessed by going to 127.0.0.1:8097/env/$data_type in your browser, $data_type means the dataset type which you are training.

Default PyTorch Adam optimizer hyper-parameters were used without learning rate scheduling. The model was trained with 100 epochs and batch size of 50 on a NVIDIA GTX 1070 GPU.

Here is tiny difference between this code and official paper. X is defined as a concatenated matrix of vertex labels、 vertex attributes and normalized node degrees.

The train loss、accuracy, test loss、accuracy are showed on visdom.

result

result

result

result

result

result

result

result