kenziyuliu/private-cross-silo-fl
[NeurIPS 2022] JAX/Haiku implementation of "On Privacy and Personalization in Cross-Silo Federated Learning"
This project helps data scientists and machine learning researchers evaluate and implement personalized machine learning models while protecting user privacy. It takes various datasets like medical images (ADNI), MNIST variations, and other public datasets, and outputs model performance metrics, allowing researchers to understand the trade-offs between personalization and privacy. This is designed for those who work with sensitive data across different organizations and need to build effective, privacy-preserving machine learning solutions.
No commits in the last 6 months.
Use this if you are a data scientist or researcher working with decentralized datasets from multiple organizations and need to build personalized machine learning models that comply with strict privacy requirements.
Not ideal if you need a plug-and-play solution for deploying federated learning in a production environment, as this is primarily a research implementation.
Stars
27
Forks
5
Language
Python
License
MIT
Category
Last pushed
Apr 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kenziyuliu/private-cross-silo-fl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
flwrlabs/flower
Flower: A Friendly Federated AI Framework
JonasGeiping/breaching
Breaching privacy in federated learning scenarios for vision and text
anupamkliv/FedERA
FedERA is a modular and fully customizable open-source FL framework, aiming to address these...
zama-ai/concrete-ml
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on...
p2pfl/p2pfl
P2PFL is a decentralized federated learning library that enables federated learning on...