-
Notifications
You must be signed in to change notification settings - Fork 2
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
edge_weight and mi loss #4
Comments
您好,我最近也在看这篇论文的代码,可以留一个联系方式,我们沟通一下吗? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thank you so much for sharing the work!but I have some doubts about the following points:
Do we not need to take the negative of the mutual information loss?Should we be minimizing the mutual information loss?
![Snipaste_2024-06-10_01-15-56](https://private-user-images.githubusercontent.com/68786052/337994764-161a7907-3a75-4f71-92a8-824ba23f632b.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.jcV2D5nQYOFoCY-7ePS6iJO-tzi29yS--q5-w2ne6lc)
Also, in the GlobalGNN module, the calculated edge_weight does not seem to be used.
![Snipaste_2024-06-10_01-16-40](https://private-user-images.githubusercontent.com/68786052/337994772-ac785990-8425-4b5a-931b-4cddf1617de1.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.E7ZX3QFJNIjuZAZGTvpbA_gIsiDbpPP9x3leHfrbAUo)
I look forward to your explanation!
非常感谢你的代码,很棒的工作!但是我对下面的几点有些疑惑,互信息损失不用取负吗,是最小化互信息损失吗,还有在globalgnn模块,所求的edge_weight,好像没有用上?期待你的解答~
The text was updated successfully, but these errors were encountered: