# DGCNN **Repository Path**: milo7hao/DGCNN ## Basic Information - **Project Name**: DGCNN - **Description**: A PyTorch implementation of DGCNN based on AAAI 2018 paper "An End-to-End Deep Learning Architecture for Graph Classification" - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-08-10 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # DGCNN A PyTorch implementation of DGCNN based on AAAI 2018 paper [An End-to-End Deep Learning Architecture for Graph Classification](https://www.cse.wustl.edu/~muhan/papers/AAAI_2018_DGCNN.pdf). ## Requirements - [Anaconda](https://www.anaconda.com/download/) - [PyTorch](https://pytorch.org) ``` conda install pytorch torchvision -c pytorch ``` - PyTorchNet ``` pip install git+https://github.com/pytorch/tnt.git@master ``` - [PyTorch Geometric](https://rusty1s.github.io/pytorch_geometric/build/html/index.html) ``` pip install torch-scatter pip install torch-sparse pip install torch-cluster pip install torch-spline-conv (optional) pip install torch-geometric ``` ## Datasets The datasets are collected from [graph kernel datasets](https://ls11-www.cs.tu-dortmund.de/staff/morris/graphkerneldatasets). The code will download and extract them into `data` directory automatically. The `10fold_idx` files are collected from [pytorch_DGCNN](https://github.com/muhanzhang/pytorch_DGCNN). ## Usage ### Train Model ``` 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. ## Benchmarks 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.

Dataset	MUTAG	PTC	NCI1	PROTEINS	D&D	COLLAB	IMDB-B	IMDB-M
Num. of Graphs	188	344	4,110	1,113	1,178	5,000	1,000	1,500
Num. of Classes	2	2	2	2	2	3	2	3
Node Attr. (Dim.)	8	19	38	5	90	1	1	1
Num. of Parameters	52,035	52,387	52,995	51,939	54,659	51,940	51,811	51,940
DGCNN (official)	85.83±1.66	58.59±2.47	74.44±0.47	75.54±0.94	79.37±0.94	73.76±0.49	70.03±0.86	47.83±0.85
DGCNN (ours)	81.67±9.64	59.12±11.27	75.72±3.13	72.88±3.38	68.80±5.37	70.52±2.00	71.50±4.48	46.47±5.22
Training Time	4.48s	6.77s	61.04s	21.15s	64.71s	202.65s	15.55s	21.90s

## Results The train loss、accuracy, test loss、accuracy are showed on visdom. ### MUTAG ![result](results/mutag.png) ### PTC ![result](results/ptc.png) ### NCI1 ![result](results/nci1.png) ### PROTEINS ![result](results/proteins.png) ### D&D ![result](results/dd.png) ### COLLAB ![result](results/collab.png) ### IMDB-B ![result](results/imdbb.png) ### IMDB-M ![result](results/imdbm.png)