AshwinRJ/Federated-Learning-PyTorch

Implementation of Communication-Efficient Learning of Deep Networks from Decentralized Data

51
/ 100
Established

This project helps machine learning engineers and researchers explore federated learning, a technique for collaboratively training models without centralizing user data. You can feed in image datasets like MNIST or CIFAR-10 and observe how different configurations of federated learning impact model accuracy, particularly when data is distributed unevenly among users. It's designed for those who need to understand or implement decentralized machine learning approaches.

1,433 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner interested in experimenting with federated learning architectures and evaluating their performance under various data distribution conditions.

Not ideal if you need a production-ready federated learning system or a tool for highly complex, real-world deployment scenarios.

federated-learning decentralized-machine-learning privacy-preserving-ai distributed-model-training machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,433

Forks

463

Language

Python

License

MIT

Last pushed

May 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AshwinRJ/Federated-Learning-PyTorch"

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