MoCoSFL

[jafermarq]

MoCoSFL

• Title: MocoSFL: enabling cross-client collaborative self-supervised learning
• Venue: ICLR 2023
• Link to paper: https://openreview.net/forum?id=2QGJXyMNoPz

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

[huangs0]

Hi @jafermarq I would like to implement the MoCoSFL baseline in the Flower framework.

Contribution plan

• Implement both the MocoSFL and TAResSFL for communication and privacy in flower + PyTorch.
• Reproduce Table 3 for cross-client accuracy performance and Table 4 for privacy evaluation.
• Further contribution might be to implement the Table 2 for communication efficiency measurement in Flower.

  Experiments/Datasets

• Dataset will be CIFAR-10, CIFAR-100 and even ImageNet-12 (low priority).
• Experiments include:
  • Performance comparison among model setup, dataset, and IIDness, corresponding to Table 3.
  • Privacy comparison on target data setup, corresponding to Table 4.
• My Background I am Songlin, a M.Phil. student in Computer Science at the University of Hong Kong supervised by Dr. Wu, Chenshu. I based in Hong Kong, which is in the list of eligible countries. You can also found me on Flower slack as (@ Songlin, Huang Songlin)

[jafermarq]

hi @huangs0, thanks for the detailed contribution plan ! Table 3 and 4 look great. I'd say before extending the experiments to ImagenNet-12, it would be more interesting to show the comparison with FL-BYOL. I think everything is set then. I have ✅ all the points in Step1&2 above and I added you as assignee to this GitHub issue. I have also moved this item to InProgress state. You can find the steps of creating your baseline following the link in the What happens next? section. Please do not hesitate reaching out over our Slack if you have some questions or if you have suggestions to improve something.

Looking forward to see MocoSFL in action, it's a cool paper!

[jafermarq]

Hi @huangs0,

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!!