NaiboWang/Data-Free-Ensemble-Selection-For-One-Shot-Federated-Learning

Data-Free Ensemble Selection For One-Shot Federated Learning

28
/ 100
Experimental

This project helps machine learning practitioners in model marketplaces efficiently combine multiple pre-trained AI models without needing access to the original training data. It takes a collection of diverse machine learning models and outputs a smaller, more effective 'ensemble' of models that performs better than any single model. This is designed for AI researchers and engineers working with federated learning or model aggregation scenarios.

No commits in the last 6 months.

Use this if you need to select the best combination of existing machine learning models to improve overall performance, especially when you cannot access the original training data for privacy or logistical reasons.

Not ideal if you are developing a brand new machine learning model from scratch or if you have full access to all the original training data and computational resources for traditional model training.

federated-learning model-aggregation ensemble-modeling machine-learning-operations ai-model-selection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

9

Forks

4

Language

Jupyter Notebook

License

Last pushed

Jul 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NaiboWang/Data-Free-Ensemble-Selection-For-One-Shot-Federated-Learning"

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