Skip to content
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

About the implementation of FedMD baseline #1

Open
horanshi opened this issue Apr 17, 2024 · 0 comments
Open

About the implementation of FedMD baseline #1

horanshi opened this issue Apr 17, 2024 · 0 comments

Comments

@horanshi
Copy link

horanshi commented Apr 17, 2024

Hi,
I have a few questions for the implementation of FedMD baseline, will these affect the performance of FedMD?
(1)In the FedMD paper, it should perform digest(distillation) first, and after that perform revisit(train on local dataset). But the code in this repository place the revisit before the digest.
(2)In the FedMD paper, the client should also train the public dataset before doing the communication(digest and revisit).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant