-
Notifications
You must be signed in to change notification settings - Fork 842
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
Add FedPFT baseline #3268
Add FedPFT baseline #3268
Conversation
Hi @mahdibeit , i did a couple of small fixes. now the test pipeline starts but you'll notice that |
Hi @jafermarq, thanks for taking the time to fix the issues. I noticed that the test-baseline.sh script that I ran did not do all the tests (like mypy or lint). I fixed all the issues this time and ran it successfully without errors. Let me know if it requires any further changes. |
@mahdibeit , cool. The tests pass. I'll take a closer look into the code today/tomorrow and get back to you if i see something that we could improve. In most baselines, contributors decided to add their contact details (e.g. email address) in the |
Awesome. Thank you so much @jafermarq. I look forward to your review. Thanks for your suggestion. I added my email to the README file. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi @mahdibeit , I was able to reproduce the results you show in the plot at the end of your README.md
(but needed to make the small changes i suggest in my review below). Let me know what you think.
The PR is in a pretty good state so once those small issues are resolved it can be merged 🙌
update readme Co-authored-by: Javier <jafermarq@users.noreply.github.com>
fix config arg Co-authored-by: Javier <jafermarq@users.noreply.github.com>
Hi @jafermarq, that is great news. I merged the suggested changes. Everything looks great to me. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great! FedPFT
is great and really fast! 🚀
Co-authored-by: jafermarq <javier@flower.ai>
Issue
Description
This PR adds FedPFT baseline as introduced in the "Parametric Feature Transfer: One-shot Federated Learning with Foundation Models" paper.
Related issues/PRs
Implements #3232
Proposal
Explanation
Implements FedPFT as a baseline.
Checklist
#contributions
)Changelog entry
Any other comments?