Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Theheavens 40fc6fddad | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
dgi_trainer.py | 1 year ago |
Run with following:
# use tensorflow backend
TL_BACKEND=paddle python dgi_trainer.py --dataset cora --lr 0.002 --patience 50
TL_BACKEND=paddle python dgi_trainer.py --dataset citeseer --lr 0.0005 --patience 20 --n_epoch 300
TL_BACKEND=paddle python dgi_trainer.py --dataset pubmed --lr 0.001 --hidden_dim 256 --patience 20
# use paddle backend
TL_BACKEND=tensorflow python dgi_trainer.py --dataset cora --lr 0.003 --patience 50
TL_BACKEND=tensorflow python dgi_trainer.py --dataset citeseer --lr 0.001 --patience 20 --n_epoch 100
TL_BACKEND=tensorflow python dgi_trainer.py --dataset pubmed --hidden_dim 256 --lr 0.001
# use pytorch backend
TL_BACKEND=torch python dgi_trainer.py --dataset cora
TL_BACKEND=torch python dgi_trainer.py --dataset citeseer
TL_BACKEND=torch python dgi_trainer.py --dataset pubmed --lr 0.001 --patience 20
Dataset | Cora | Citeseer | Pubmed |
---|---|---|---|
Author's Code | 82.3 | 71.8 | 76.8 |
DGL | 81.6 | 69.4 | 76.1 |
GammaGL(tf) | 81.51 ± 0.55 | 69.01 ± 0.91 | 78.37 ± 0.37 |
GammaGL(th) | --.- | --.- | 79.58 ± 0.52 |
GammaGL(pd) | 81.19 ± 0.64 | 69.06 ± 0.50 | 78.58 ± 0.65 |
GammaGL(ms) | --.- | --.- | --.- |
No Description
Python Cuda C++ Cython Markdown other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》