关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
GAMMALab
/
OpenHGNN
Not watched
23
25
Fork 44
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 2 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
677 Commits
3 Branches
33 MiB
5735 Download
 
 
 
Branch: main
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'main'
${ noResults }
OpenHGNN/openhgnn/output/GATNE-T
Hongyi Zhang 8daa34c9a2 [Model] GATNE performance 2 years ago
..
README.md [Model] GATNE performance 2 years ago

README.md

GATNE [KDD2019]

Paper: [GATNE] Representation Learning for Attributed Multiplex Heterogeneous Network

Code from author: https://github.com/THUDM/GATNE

Code from dgl: https://github.com/dmlc/dgl/tree/master/examples/pytorch/GATNE-T

How to run

Clone the OpenHGNN

python main.py -m GATNE-T -t link_prediction -d HGBl-amazon -g 0 --use_best_config

If you do not have gpu, set -gpu -1.

Candidate dataset:

HGBl-amazon

Performance

Link Prediction

Evaluation metric: roc_auc

HGBl-amazon
0.7300(product-product-0) 0.8866(product-product-1) 0.8083(avgerage)

Contirbutor

Hongyi Zhang[GAMMA LAB]

If you have any questions,

Submit an issue or email to zhanghongyi@bupt.edu.cn.

Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

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

Please read the following content carefully:

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》

Agree and continue
Disagree, exit