You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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).
The text was updated successfully, but these errors were encountered:
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).
The text was updated successfully, but these errors were encountered: