https://github.com/snap-stanford/GraphGym

Platform for designing and evaluating Graph Neural Networks (GNN)
https://github.com/snap-stanford/GraphGym

Last synced: about 2 months ago
JSON representation

Platform for designing and evaluating Graph Neural Networks (GNN)

• Host: GitHub
• URL: https://github.com/snap-stanford/GraphGym
• Owner: snap-stanford
• License: other
• Created: 2020-10-14T05:01:35.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2023-11-10T05:37:18.000Z (about 1 year ago)
• Last Synced: 2024-10-15T05:40:54.712Z (2 months ago)
• Language: Python
• Homepage:
• Size: 10.8 MB
• Stars: 1,696
• Watchers: 24
• Forks: 185
• Open Issues: 23
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - snap-stanford/GraphGym - aware Graph Neural Networks一种身份感知图神经网络对现有的消息传递 GNN 进行了扩展，将其性能提升到了高于 1-WL 测试的水平。实验结果表明，将现有的 GNN 转变为 ID-GNN 可以在难以分类的节点预测、边预测、图属性预测任务中获得平均 40% 的准确率提升；在节点和图分类对比基准任务获得 3%的准确率提升；链接预测任务获得 15% 的ROC提升。 (其他_图神经网络GNN / 网络服务_其他)