Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Guangyu Zhou eaa51ac4dc | 3 months ago | |
---|---|---|
.. | ||
readme.md | 10 months ago | |
tadw_trainer.py | 3 months ago |
Dataset | # Nodes | # Edges | # Classes |
---|---|---|---|
Cora | 2,708 | 10,556 | 7 |
Citeseer | 3,327 | 9,228 | 6 |
Refer to Planetoid.
For all the datasets: The training ratio is 50% for linear SVM.
Dataset | Paper(10%) | Paper(20%) | Paper(30%) | Paper(40%) | Paper(50%) | Our(tf) | Our(th) | Our(pd) | Our(ms) |
---|---|---|---|---|---|---|---|---|---|
Cora | 82.4 | 85.0 | 85.6 | 86.0 | 86.7 | 84.43(±0.37) | 84.42(±0.96) | 84.34(±0.64) | 84.08(±0.53) |
Citeseer | 70.6 | 71.9 | 73.3 | 73.7 | 74.2 | 74.09(±1.11) | 74.41(±0.58) | 73.92(±0.72) | 73.87(±0.57) |
TL_BACKEND="tensorflow" python tadw_trainer.py --dataset cora --lr 0.2 --n_epoch 100 --embedding_dim 80 --lamda 0.2 --svdft 200
TL_BACKEND="torch" python tadw_trainer.py --dataset cora --lr 0.2 --n_epoch 100 --embedding_dim 80 --lamda 0.2 --svdft 200
TL_BACKEND="paddle" python tadw_trainer.py --dataset cora --lr 0.2 --n_epoch 100 --embedding_dim 80 --lamda 0.2 --svdft 200
TL_BACKEND="mindspore" python tadw_trainer.py --dataset cora --lr 0.2 --n_epoch 100 --embedding_dim 80 --lamda 0.2 --svdft 200
TL_BACKEND="torch" python tadw_trainer.py --dataset citeseer --lr 0.1 --n_epoch 50 --embedding_dim 500 --lamda 0.5 --svdft 300
TL_BACKEND="tensorflow" python tadw_trainer.py --dataset citeseer --lr 0.1 --n_epoch 50 --embedding_dim 500 --lamda 0.5 --svdft 300
TL_BACKEND="paddle" python tadw_trainer.py --dataset citeseer --lr 0.1 --n_epoch 50 --embedding_dim 500 --lamda 0.5 --svdft 300
TL_BACKEND="mindspore" python tadw_trainer.py --dataset citeseer --lr 0.1 --n_epoch 50 --embedding_dim 500 --lamda 0.5 --svdft 300
No Description
Python C++ Cuda Markdown Text
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》