Nokia-Bell-Labs/data-centric-federated-learning

Enhancing Efficiency in Multidevice Federated Learning through Data Selection

35
/ 100
Emerging

This framework helps machine learning engineers and researchers train deep neural networks more efficiently on a wide variety of personal devices, like smartphones or IoT sensors, without compromising user privacy. It takes raw data from many decentralized devices and, through a selective process, produces a more accurate and faster-to-train machine learning model. This is designed for those managing large-scale federated learning deployments.

No commits in the last 6 months.

Use this if you are developing or deploying machine learning models across many resource-constrained devices and need to improve training efficiency and model accuracy.

Not ideal if your machine learning models are trained on centralized, powerful servers with abundant computational resources and no privacy constraints.

federated-learning edge-computing deep-learning-optimization privacy-preserving-ai mobile-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

13

Forks

3

Language

Python

License

BSD-3-Clause-Clear

Last pushed

Apr 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Nokia-Bell-Labs/data-centric-federated-learning"

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