SSFL + KWS

[jafermarq]

SSFL + KWS

• Title: Semi-Supervised Federated Learning for Keyword Spotting
• Venue: ICME 2023
• Link to paper: https://arxiv.org/abs/2305.05110

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

[Nisarg143]

Hi @jafermarq !!

I would like to implement the this baseline (SSFL + KWS) in the flower framework

This is the contribution plan I'd like to propose:

--> I would like to implement and recreate the SSL baseline (Fig. 2). --> By implementing this thing, I would like to recreate the Table 1 and Table 2 which are the main table of the paper. --> If the time permits, I would also like to replicate the results present in the figure 3 and 4.

Let me know your thoughts and give your feedback on what can be done in the given time frame.

Thanks, Nisarg Patel

[jafermarq]

Hi again @Nisarg143 ! This is an interesting paper. Having Tables 1 & 2 make sense. Before going ahead I just want to be sure you are comfortable implementing this paper under 2 months and that you have access to resources to do so (for example, dedicated access to one semi-powerful GPU should be enough, but Google Colab won't be suitable for this baseline, at least not the free tier). There are quite a few experiments in Table 1 (there are all variations of the same experiment but still, they need to be run separately and multiple times each to measure so you can report mean and standard deviation). I'm just bringing up these topics in part because I don't see much activity in your GitHub profile... I might be mislead by that, so please tell me if so.

[Nisarg143]

Hi again @jafermarq,

Thank you for your response.

Thank you for bringing up the fact that this requires a good amount of computing power which I can manage as I do have access to GPU. Talking about the implementation in time, I will give my best and my previous research experience would really help me in this case as I’ve already worked in FL. Here’s a google scholar link: https://scholar.google.com/citations?user=Mwd7y2QAAAAJ&hl=en&oi=ao for your reference. I’ve done two papers GeFL and LEAF which are aligned with the FL application in different domains.

The chosen paper is an application of the FL in different domain and I really want to explore and contribute to this.

Thank you, Nisarg Patel

[jafermarq]

Hi @Nisarg143, thanks for the info and the links to your papers, I'll check them!! this SSFL+KWS baseline is all yours now 🙌, having Tables 1 &2 as you proposed make sense to have as part of the Summer of Reproducibility. I have now ✅ all points above for Step 1 & 2, I have added you as the assignee to this issue, and changed this baseline's status to In Progress. The best place to start with the code is the guide you'll find following the link in the What happens next? section in the issue description.

If you have some doubts along the way, please reach out to me or the other contributors via the Flower Slack.

It's great having you onboard and I'm looking forward to see this baseline in action with SpeechCommands !!

[jafermarq]

Hi @Nisarg143 ! 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!!