项目文件夹

文件

T

文件历史

Tianyi cdbeb17f2d [Model] Simplifying Graph Convolutional Networks. (#405 )

* [Model] Simplifying Graph Convolutional Networks.

* - improve code stype (use nn.Linear)
- use `bias` option
- update hyperparameter and corresponding performance

2019-02-22 15:17:26 +08:00

README.md

[Model] Simplifying Graph Convolutional Networks. (#405 )

2019-02-22 15:17:26 +08:00

sgc.py

[Model] Simplifying Graph Convolutional Networks. (#405 )

2019-02-22 15:17:26 +08:00

README.md

Simple Graph Convolution (SGC)

Paper link: Simplifying Graph Convolutional Networks
Author's code repo: https://github.com/Tiiiger/SGC.

Dependencies

PyTorch 0.4.1+
requests

bash pip install torch requests

Codes

The folder contains an implementation of SGC (sgc.py).

Results

Run with following (available dataset: "cora", "citeseer", "pubmed")

python sgc.py --dataset cora --gpu 0
python sgc.py --dataset citeseer --weight-decay 5e-5 --n-epochs 150 --bias --gpu 0
python sgc.py --dataset pubmed --weight-decay 5e-5 --bias --gpu 0

On NVIDIA V100

cora: 0.819 (paper: 0.810), 0.0008s/epoch
citeseer: 0.725 (paper: 0.719), 0.0008s/epoch
pubmed: 0.788 (paper: 0.789), 0.0007s/epoch