dmlc--dgl
9a0511c8e9
* upd * damn it * fuck * fuck pylint * fudge * remove some comments about MXNet * upd * upd * damn it * damn it * fuck * fuck * upd * upd * pylint bastard * upd * upd * upd * upd * upd * upd * upd * upd * upd
833 B
833 B
Simple Graph Convolution (SGC)
- Paper link: Simplifying Graph Convolutional Networks
- Author's code repo: https://github.com/Tiiiger/SGC.
Dependencies
- MXNET 1.5+
- 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")
DGLBACKEND=mxnet python3 sgc.py --dataset cora --gpu 0
DGLBACKEND=mxnet python3 sgc.py --dataset citeseer --weight-decay 5e-5 --n-epochs 150 --bias --gpu 0
DGLBACKEND=mxnet python3 sgc.py --dataset pubmed --weight-decay 5e-5 --bias --gpu 0
On NVIDIA V100
- cora: 0.818 (paper: 0.810)
- citeseer: 0.725 (paper: 0.719)
- pubmed: 0.788 (paper: 0.789)