Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Theheavens 299b0523f9 | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago |
Paper: Network Schema Preserving Heterogeneous Information Network Embedding
Code from author: https://github.com/Andy-Border/NSHE
Clone the Openhgnn-DGL
python main.py -m NSHE -t node_classification -d acm4NSHE -g 0 --use_best_config
If you do not have gpu, set -gpu -1.
Node classification | Macro-F1 | Micro-F1 |
---|---|---|
paper | 83.27 | 84.12 |
OpenHGNN | 84.78 | 84.95 |
We process the acm dataset given by NSHE. It saved as dgl.heterograph and can be loaded by dgl.load_graphs
You can download the dataset by
wget https://s3.cn-north-1.amazonaws.com.cn/dgl-data/dataset/acm4NSHE.zip
Or run the code mentioned above and it will download automaticlly.
Note: [TODO] We will use the dataloader to combine the two sampler without storing the temporal file and use mini-batch trainer to improve the training efficiency.
num_e_neg = 2 # number of negative edges
num_ns_neg = 3 # number of negative schemas
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》