Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Theheavens ab25b83431 | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago |
Clone the Openhgnn-DGL
python main.py -m RSHN -t node_classification -d aifb -g 0
If you do not have gpu, set -gpu -1.
Supported Dataset: RDFDataset
Method | AIFB | MUTAG | BGS | AM |
---|---|---|---|---|
RSHN | 97.22 | 82.35 | 93.10 | 90.40 |
RSHN(openhgnn) | 97.22 | 85.29 | 93.10 | 89.39 |
The experiments in RSHN have serious problems according to the official code. First, it does not use validation set, and just tune hyperparameters on test set. Second, it reports the accuracy at the epoch with best accuracy on test set in the paper. And in this setting, we give our performance.
You can modify the parameters in openhgnn/config.ini
# The next two hyper-parameters are used in building the coarsened-line graph.
rw_len = 5
batch_size = 1000
# edga_layer means number of CL-GNN layers, node_layer means number of H-GNN layers
num_node_layer = 2
num_edge_layer = 1
Best config can be found in best_config
Tianyu Zhao[GAMMA LAB]
Submit an issue or email to tyzhao@bupt.edu.cn.
OpenHGNN是由北邮GAMMA Lab开发的基于PyTorch和DGL的开源异质图神经网络工具包。
Python Markdown Shell
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》