owkin/FLamby

Cross-silo Federated Learning playground in Python. Discover 7 real-world federated datasets to test your new FL strategies and try to beat the leaderboard.

42
/ 100
Emerging

FLamby provides a standardized way to test and compare different federated learning approaches, especially in healthcare. It takes raw medical imaging data, clinical records, or other health-related datasets from multiple sources, automatically preprocesses them, and outputs performance metrics for various federated learning strategies. This is designed for machine learning researchers and practitioners in medical or health informatics who are developing or evaluating federated learning models.

230 stars. No commits in the last 6 months.

Use this if you need a reliable benchmark to evaluate new federated learning algorithms on real-world, naturally partitioned healthcare datasets without centralizing sensitive patient information.

Not ideal if you are looking for actual datasets to use in production, as FLamby only provides data loaders and benchmark code, not the raw data itself.

federated-learning medical-imaging healthcare-AI distributed-machine-learning biomedical-informatics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

230

Forks

29

Language

Python

License

MIT

Last pushed

Jun 19, 2024

Commits (30d)

0

Get this data via API

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

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