Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/leftthomas/DGCNN
A PyTorch implementation of DGCNN based on AAAI 2018 paper "An End-to-End Deep Learning Architecture for Graph Classification"
https://github.com/leftthomas/DGCNN
gcn gnn graph graph-classification graph-convolutional-networks pytorch
Last synced: about 2 months ago
JSON representation
A PyTorch implementation of DGCNN based on AAAI 2018 paper "An End-to-End Deep Learning Architecture for Graph Classification"
- Host: GitHub
- URL: https://github.com/leftthomas/DGCNN
- Owner: leftthomas
- Created: 2018-01-18T11:24:39.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2023-08-10T05:36:10.000Z (about 1 year ago)
- Last Synced: 2024-07-16T18:11:39.351Z (2 months ago)
- Topics: gcn, gnn, graph, graph-classification, graph-convolutional-networks, pytorch
- Language: Python
- Homepage:
- Size: 36.6 MB
- Stars: 59
- Watchers: 2
- Forks: 15
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-graph-classification - [Python Alternative
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
### PTC
### NCI1
### PROTEINS
### D&D
### COLLAB
### IMDB-B
### IMDB-M
