ChristianInterno/FedLEx

Federated Loss Exploration for Improved Convergence on Non-IID Data (IJCNN2024)

12
/ 100
Experimental

This project helps researchers working with federated learning models achieve better and more robust model performance, especially when their data is not uniformly distributed across different clients. It takes your federated learning setup, where clients contribute data for a shared model, and provides a method to create a 'global guidance matrix.' This matrix then helps clients improve their gradient updates, leading to a more accurate and stable global model. Researchers and machine learning practitioners who deploy federated learning models would use this.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer struggling with poor convergence or unstable performance in federated learning models due to non-IID (non-identically and independently distributed) data across your clients.

Not ideal if your federated learning data is already identically and independently distributed across clients, or if you are not working with federated learning at all.

federated-learning distributed-machine-learning non-IID-data model-convergence neural-networks
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Last pushed

Feb 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ChristianInterno/FedLEx"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.