Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
hanhui 1ffb6b2e13 | 1 year ago | |
---|---|---|
.. | ||
readme.md | 1 year ago | |
rgcn_trainer.py | 1 year ago |
Paper: Modeling Relational Data with Graph Convolutional Networks
Author's code for entity classification: https://github.com/tkipf/relational-gcn
Author's code for link prediction: https://github.com/MichSchli/RelationPrediction
Dataset | #Nodes | #Edges | #Relations | #Labeled |
---|---|---|---|---|
AIFB | 8,285 | 58,086 | 90 | 176 |
MUTAG | 23,644 | 148,454 | 46 | 340 |
BGS | 333,845 | 1,832,398 | 206 | 146 |
AM | 1,666,764 | 11,976,642 | 266 | 1000 |
TL_BACKEND="pytorch" python rgcn_trainer.py --dataset aifb --l2 5e-5
TL_BACKEND="pytorch" python rgcn_trainer.py --dataset mutag --l2_coef 5e-2
TL_BACKEND="pytorch" python rgcn_trainer.py --dataset bgs --lr 0.0001 --l2_coef 5e-2
TL_BACKEND="tensorflow" python rgcn_trainer.py --dataset aifb
TL_BACKEND="tensorflow" python rgcn_trainer.py --dataset mutag --l2_coef 5e-2
TL_BACKEND="tensorflow" python rgcn_trainer.py --dataset bgs --l2_coef 5e-2
TL_BACKEND="paddle" python rgcn_trainer.py --dataset aifb
TL_BACKEND="paddle" python rgcn_trainer.py --dataset mutag --l2_coef 5e-2
TL_BACKEND="paddle" python rgcn_trainer.py --dataset bgs --l2_coef 5e-2
Dataset | Paper | Our(th) | Our(tf) | Our(pd) |
---|---|---|---|---|
AIFB | 95.83 | 96.11(±1.52) | 94.17(±2.05) | 95.56(±2.3) |
MUTAG | 73.23 | 85.0(±0.66) | 85.29(±1.20) | 85.00(±1.9) |
BGS | 83.10 | 74.1(±1.7) | 73.79(±1.9) | 73.56(±3.8) |
AM | 89.29 |
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》