Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Guangyu Zhou eaa51ac4dc | 3 months ago | |
---|---|---|
.. | ||
hgt_trainer.py | 3 months ago | |
readme.md | 1 year ago |
Dataset | # Nodes | # Node Types | # Edges | # Edge Types | Target | # Classes |
---|---|---|---|---|---|---|
DBLP | 26,128 | 4 | 239,566 | 6 | author | 4 |
IMDB | 21,420 | 4 | 86,642 | 6 | movie | 5 |
DBLP dataset refer to HGBDataset.
IMDBdataset refer to IMDB.
# available dataset: "DBLP", "IMDB"
TL_BACKEND="paddle" python hgt_trainer.py --dataset DBLP --lr 0.0001 --n_epoch 200 --hidden_dim 1024 --l2_coef 1e-6 --heads 4 --drop_rate 0.9
TL_BACKEND="torch" python hgt_trainer.py --dataset DBLP --lr 0.0001 --n_epoch 200 --hidden_dim 1024 --l2_coef 5e-6 --heads 4 --drop_rate 0.9
TL_BACKEND="paddle" python hgt_trainer.py --dataset IMDB --lr 0.0001 --n_epoch 200 --hidden_dim 1024 --l2_coef 1e-6 --heads 4 --drop_rate 0.9
TL_BACKEND="torch" python hgt_trainer.py --dataset IMDB --lr 0.0001 --n_epoch 150 --hidden_dim 1024 --l2_coef 1e-6 --heads 4 --drop_rate 0.5
TL_BACKEND="tensorflow" python hgt_trainer.py --dataset IMDB --lr 0.0001 --n_epoch 200 --hidden_dim 1024 --l2_coef 5e-6 --heads 4 --drop_rate 0.9
Dataset | Paper | Our(pd) | Our(tf) | Our(torch) |
---|---|---|---|---|
DBLP | 93.01±0.23 | 92.4(±0.92) | 90.89(±1.08) | |
IMDB | 63.00±1.19 | 54.51(±1.99) | 55.98(±2.09) | 54.93(±1.34) |
The experimental results under IMDB dataset are consistent with PyG.
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》