Open jafermarq opened 1 year ago
Hi @jafermarq. I'm a first-year PhD student in Singapore. I'd like to pick up this issue and reproduce Scaffnew's results in Fig. 1 and Fig.2 w/ logistic regression and LIBSVM w8a dataset.
Hi @duynht , thanks for expressing your interest to work on scaffnew
. However, this baseline is already In Progress as it is been worked on by Konstantin (the author of the paper).
I realized that I never posted the plan that we discussed with @jafermarq on Zoom, so here it is.
The proposed experiments:
For all 3 of the above, that includes a comparison to Scaffold and FedAvg (all clients sampled in each round since this is the setting of Scaffnew)
I realize I'm posting this very close to the deadline but it'd be a shame to drop the baseline since I've already worked on it.
Scaffnew
Do you want to work on this baseline?
What follows are the steps 1 & 2 in the Summer of Reproducibility instructions.
1. Join the Summer of Reproducibility program
#summer-of-reproducibility
.2. Define the scope of your contribution
[ ] Check if you are eligible for a reward.
If where you are based is not on the list, please send us an email (
summer@flower.dev
) letting us know a bit about yourself (where are you currently based?, are you a university student? do you work at a public institution?). Please tell us the baselines you are interested in implementing (i.e. tell us your GitHub issue if you have crated one). We will reach back to you.What happens next?
[ ] This item will be moved to the
In Progress
stage by a member of the Flower Team.[ ] Follow the instructions for creating a new baseline which will guide you through the process step-by-step.
Is something wrong or not clear ?