feat(baselines): Add FedLC

[flydump]

Issue

Description

Adds FedLC (Federated Learning with Label Distribution Skew via Logits Calibration) baseline

Related issues/PRs

Proposal

Explanation

Merge baseline

Checklist

• Implement proposed change
• Write tests
• Update documentation
• Make CI checks pass
• Ping maintainers on Slack (channel #contributions)

Any other comments?

This PR is still very much still work in progress. I have found it hard to reproduce the results from the paper due to lack of experimental details.

[jafermarq]

Hello @flydump 👋 , great to see a PR open for FedLC. Let us know when you'd like us to do a first review. Also, do not hesitate to ask questions if you have some doubts on how to implement certain aspects of the FedLC logic using Flower. Happy to help!!

[flydump]

Hello @flydump 👋 , great to see a PR open for FedLC. Let us know when you'd like us to do a first review. Also, do not hesitate to ask questions if you have some doubts on how to implement certain aspects of the FedLC logic using Flower. Happy to help!!

Thanks, unfortunately I haven't been able to reproduce the results of the paper reliably despite my best efforts (I have compiled my latest results in the README if you'd like to take a look). So I'm probably going to pause further development on this baseline.