Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Andrei Ivanov 2584f3af10 | 9 months ago | |
---|---|---|
.. | ||
README.md | 3 years ago | |
model.py | 1 year ago | |
train_acm.py | 9 months ago |
Alternative PyTorch-Geometric implementation
“Heterogeneous Graph Transformer” is a graph neural network architecture that can deal with large-scale heterogeneous and dynamic graphs.
This toy experiment is based on DGL's official tutorial. As the ACM datasets doesn't have input feature, we simply randomly assign features for each node. Such process can be simply replaced by any prepared features.
The reference performance against R-GCN and MLP running 5 times:
Model | Test Accuracy | # Parameter |
---|---|---|
2-layer HGT | 0.465 ± 0.007 | 2,176,324 |
2-layer RGCN | 0.392 ± 0.013 | 416,340 |
MLP | 0.132 ± 0.003 | 200,974 |
No Description
Python C++ Jupyter Notebook Cuda Text 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》