Skip to content
This repository has been archived by the owner on Jul 18, 2024. It is now read-only.

Is there any details about D-SGD and FedAvg? #3

Open
zj-jayzhang opened this issue Aug 19, 2020 · 1 comment
Open

Is there any details about D-SGD and FedAvg? #3

zj-jayzhang opened this issue Aug 19, 2020 · 1 comment

Comments

@zj-jayzhang
Copy link

Absolutely,it's a good job! I am very interested in this work and I have read about your paper(both PFNM and FedMA),and I run the experiments mentioned in the paper. here is my question :

How to run the experiments about FedAvg and D-SGD,as mentioned in your paper, it seems that only PFNM available now.

Thank you.

@SC19099
Copy link

SC19099 commented Aug 21, 2020

Excuse me, have you run the multilayer PFNM? I set the net_config as "784, 100, 100, 10"(mnist) and found that only the first hidden layer of the global network got trained...

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

No branches or pull requests

2 participants