Skip to content

Add Flower Baseline: TraceFL #5245

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

Open
14 tasks done
ibrahim-Cypher10 opened this issue Apr 15, 2025 · 3 comments
Open
14 tasks done

Add Flower Baseline: TraceFL #5245

ibrahim-Cypher10 opened this issue Apr 15, 2025 · 3 comments
Assignees
Labels

Comments

@ibrahim-Cypher10
Copy link

ibrahim-Cypher10 commented Apr 15, 2025

Paper

Gill et al., 2023, "TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance", accepted at the 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE). This baseline replicates key experiments from the paper, focusing on neuron-level provenance to identify client contributions in federated learning (FL) settings.

Link

https://arxiv.org/abs/2312.13632

Maybe give motivations about why the paper should be implemented as a baseline.

TraceFL introduces a novel interpretability framework for FL by tracing neuron-level contributions from clients to the global model's predictions. This approach addresses the challenge of attributing predictions to specific clients, which is crucial for debugging, accountability, and incentivization in FL systems. By integrating TraceFL as a Flower baseline, we provide researchers with a tool to analyze and understand client contributions, enhancing transparency and trust in FL deployments.

Is there something else you want to add?

No response

Implementation

To implement this baseline, it is recommended to do the following items in that order:

For first time contributors

Prepare - understand the scope

  • Read the paper linked above
  • Decide which experiments you'd like to reproduce. The more the better!
  • Follow the steps outlined in Add a new Flower Baseline.
  • You can use as reference other baselines that the community merged following those steps.

Verify your implementation

  • Follow the steps indicated in the EXTENDED_README.md that was created in your baseline directory
  • Ensure your code reproduces the results for the experiments you chose
  • Ensure your README.md is ready to be run by someone that is no familiar with your code. Are all step-by-step instructions clear?
  • Ensure running the formatting and typing tests for your baseline runs without errors.
  • Clone your repo on a new directory, follow the guide on your own README.md and verify everything runs.
@WilliamLindskog
Copy link
Contributor

Hi @ibrahim-Cypher10, thank you for suggesting this baseline.

Is this something that you intend to work on? If so, could you please see to that you have completed all the check boxes above and that you know how to proceed with opening a PR straight from your fork of the Flower repo?

We can help you from thereon, supporting you in reviewing the baseline and seeing to that it gets merged.

If you have any questions, feel free to post them here.

@WilliamLindskog
Copy link
Contributor

Thanks for opening the PR @ibrahim-Cypher10. We will take a look at it and get back to you as soon as possible.

@WilliamLindskog WilliamLindskog added this to the Future Release milestone May 2, 2025
@ibrahim-Cypher10
Copy link
Author

Hi @WilliamLindskog , thank you for following up.

I’ve just pushed an updated version that incorporates all the requirements outlined in the checklist above. Please feel free to let me know if there’s anything else missing or that could be improved. I’m happy to make the changes.

Looking forward to your feedback.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

3 participants