FedSMOO

[jafermarq]

FedSMOO

• Title: Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape
• Venue: ICML 2023
• Link to paper: https://arxiv.org/abs/2305.11584

Do you want to work on this baseline?

🌻 Check everything about the Summer of Reproducibility on flower.dev/summer

All available baselines are listed in the Summer of Reproducibility Dashboard and also in the GitHub Issues with the summer-of-reproducibility label. The content is the same.

📝 It is advised to complete these steps before your start working on your code. But if you can't wait to implement your baseline with Flower (we totally understand it 😄), please ensure you follow the steps on how to contribute a new baseline.

What follows are the steps 1 & 2 in the Summer of Reproducibility instructions.

1. Join the Summer of Reproducibility program

• [x] Join the Flower Slack and say "hi! 👋" in the channel #summer-of-reproducibility.
• [x] Pick a baseline from our curated list <---------------------------------------- [you are doing this now]

  2. Define the scope of your contribution

• [x] What are you going to reproduce? Add a comment to your issue and tell us about your plan regarding this baseline: what experiments from the paper are you reproducing?, for which datasets ? the more details you provide us with the better !

• [x] Check if you are eligible for a reward.

  As we have to comply with US/EU regulations, we have checked that individual contributors based on these countries or territories are eligible: Australia, Austria, Belgium, Bulgaria, Canada, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, France, Germany, Gibraltar, Greece, Hong Kong SAR China, Hungary, India, Ireland, Italy, Japan, Latvia, Liechtenstein, Lithuania, Luxembourg, Malta, Mexico, Netherlands, New Zealand, Norway, Poland, Portugal, Romania, Singapore, Slovakia, Slovenia, South Korea, Spain, Sweden, Switzerland, Thailand, United Arab emirates, United Kingdom United States.

  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.

• [x] We will discuss with you about your contribution plan, if it sounds like a substantial enough contribution according to the Summer of Reproducibility rules (check our website flower.dev/summer), you'll get the OK from us to start working on your baseline!

What happens next?

• [x] 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 ?

• Ask a question directly in your issue.
• Reach out to us via the Flower Slack and ask your question in the #summer-of-reproducibility channel
• Check all the details (including FAQ) in the Summer of Reproducibility website: flower.dev/summer

[kumar-devesh]

Hi @jafermarq! I would like to work towards contributing FedSMOO to flower baselines.

Contribution Plan

• Implementing the FedSMOO Algorithm for ResNet18 with GroupNorm Layers, using the SAM objective proposed in the paper (Algorithm 1)
• Reproducing experiments on CIFAR 10/100 datasets in the mentioned settings, validating results and comparing with FedAvg, FedAdam, SCAFFOLD, FedCM, FedDyn, FedSAM, and MoFedSAM results. (Table 1)

Looking forward to working on this!

[jafermarq]

Hi @kumar-devesh , it's great to hear you want to participate in the Flower Summer of Reproducibility implementing FedSMOO. Your contribution plan is very ambitious! Are you sure that, with the time remaining for this initiative (it ends at the end of September) and the compute (i.e. GPUs) resources you have available, you can reproduce not only the FedSMOO rows in Table 1 but also those of the other methods you mention?

[kumar-devesh]

Might not be able to reproduce experiments for all but I would be able to run experiments for methods for which there is an open-sourced implementation like FedSAM and FedDyn. Compute resources should not be a problem @jafermarq.

[jafermarq]

@kumar-devesh, how about reducing the list of methods to FedAvg and FedDyn (but bear in mind it should be implemented with Flower and integrated with the rest of your codebase)? FedAvg is more like a reference (and that works better than FedAdam in Table 1) and FedDyn is a competitive baseline close to the proposed FedSMOO method.

[kumar-devesh]

Thanks for your suggestion @jafermarq, this sounds doable.

[jafermarq]

ok. Happy to have you then implementing FedSMOO with Flower. I have now ✅ all points in Step 1 & 2 above, adde you as the assignee to this GitHub issue and moved your baseline to In Progress stage. You can find how to start with the code following the link shown in the What happens next? section above. Please note that the code should follow the structure of the template directory we provided (as described in the guide). Also, the Flower Summer of Reproducibility runs until the end of September so you are advised to start with your codebase and then experiments to reproduce the results as soon as possible. You are very welcome to reach out to me and other contributors via our Slack if you have some questions or suggestions on how to improve things.

Looking forward to seeing your FedSMOO implementation with Flower!

[jafermarq]

Hi @kumar-devesh,

This is just a gentle reminder that the Flower Summer of Reproducibility is ending at the end of the month. With just a little more than 3 weeks to go, we are excited to see quite a few baselines well ahead in the process with their respective PRs close to ready. If your PR is already on the list, great !! Please make sure the PR is linked to this issue (you just need to copy the URL of this issue somewhere in the main message of your PR). Ping me when you'd like me to take a look.

Also, make sure you keep an eye:eyes: on the #summer-of-reproducibility channel in the Flower Slack. I’ll announce very soon a new (the third!) round of 1:1 ask-me-anything sessions to help Summer of Reproducibility contributors like yourself to meet the deadline. Please consider booking a time slot if you want to chat with me about your baseline, potential issues you have making your code run, how to open a PR, doubts about what to include in your readme, how to use Hydra configs more effective, etc … all questions are welcome!!