Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
中健 ab20a4b556 | 1 year ago | |
---|---|---|
.. | ||
chebnet_trainer.py | 1 year ago | |
readme.md | 1 year ago |
Dataset | # Nodes | # Edges | # Classes |
---|---|---|---|
Cora | 2,708 | 10,556 | 7 |
Citeseer | 3,327 | 9,228 | 6 |
Pubmed | 19,717 | 88,651 | 3 |
Refer to Planetoid.
# k=2, available dataset: "cora", "citeseer", "pubmed"
TL_BACKEND="paddle" python chebnet_trainer.py --k 2 --dataset cora --lr 0.01 --hidden_dim 64 --drop_rate 0.8 --l2_coef 0.0005
TL_BACKEND="tensorflow" python chebnet_trainer.py --k 2 --dataset cora --lr 0.01 --hidden_dim 64 --drop_rate 0.7 --l2_coef 0.0005
TL_BACKEND="torch" python chebnet_trainer.py --k 2 --dataset cora --lr 0.01 --hidden_dim 64 --drop_rate 0.7 --l2_coef 0.0005
TL_BACKEND="paddle" python chebnet_trainer.py --k 2 --dataset citeseer --lr 0.01 --hidden_dim 32 --drop_rate 0.9 --l2_coef 0.0005
TL_BACKEND="tensorflow" python chebnet_trainer.py --k 2 --dataset citeseer --lr 0.01 --hidden_dim 64 --drop_rate 0.9 --l2_coef 0.0005
TL_BACKEND="torch" python chebnet_trainer.py --k 2 --dataset citeseer --lr 0.01 --hidden_dim 64 --drop_rate 0.9 --l2_coef 0.0005
TL_BACKEND="paddle" python chebnet_trainer.py --k 2 --dataset pubmed --lr 0.01 --hidden_dim 64 --drop_rate 0.6 --l2_coef 0.0005
TL_BACKEND="tensorflow" python chebnet_trainer.py --k 2 --dataset pubmed --lr 0.01 --hidden_dim 64 --drop_rate 0.6 --l2_coef 0.0005
# k=3, available dataset: "cora", "citeseer"
TL_BACKEND="paddle" python chebnet_trainer.py --k 3 --dataset cora --lr 0.01 --hidden_dim 64 --drop_rate 0.8 --l2_coef 0.0005
TL_BACKEND="tensorflow" python chebnet_trainer.py --k 3 --dataset cora --lr 0.01 --hidden_dim 64 --drop_rate 0.7 --l2_coef 0.0005
TL_BACKEND="torch" python chebnet_trainer.py --k 3 --dataset cora --lr 0.01 --hidden_dim 64 --drop_rate 0.7 --l2_coef 0.0005
TL_BACKEND="paddle" python chebnet_trainer.py --k 3 --dataset citeseer --lr 0.01 --hidden_dim 64 --drop_rate 0.9 --l2_coef 0.0005
TL_BACKEND="torch" python chebnet_trainer.py --k 3 --dataset citeseer --lr 0.01 --hidden_dim 64 --drop_rate 0.9 --l2_coef 0.0005
K=2
Dataset | Paper | Our(pd) | Our(tf) | Our(torch) |
---|---|---|---|---|
cora | 81.2 | 80.78±1.12 | 80.62±0.80 | 80.42±1.18 |
citeseer | 69.6 | 69.45±1.75 | 70.34±1.46 | 70.58±0.62 |
pubmed | 73.8 | 76.90±1.40 | 75.68±1.42 | OOM |
K=3
Dataset | Paper | Our(pd) | Our(tf) | Our(torch) |
---|---|---|---|---|
cora | 79.5 | 81.88±1.32 | 80.55±1.75 | 81.72±1.38 |
citeseer | 69.8 | 70.27±0.93 | OOM | 70.18±0.82 |
pubmed | 74.4 | OOM | OOM | OOM |
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》