diaoenmao/SemiFL-Semi-Supervised-Federated-Learning-for-Unlabeled-Clients-with-Alternate-Training
[NeurIPS 2022] SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
This project helps machine learning researchers and data scientists improve the performance of their models, especially when they have a central labeled dataset but also access to many distributed, unlabeled datasets. It takes in a trained model on a server with labeled data and combines it with unlabeled data from various client sources, producing a more robust and accurate machine learning model without needing to share sensitive client data. This is ideal for research labs or organizations dealing with privacy-sensitive data across different entities.
No commits in the last 6 months.
Use this if you need to train high-performing machine learning models using both a small labeled dataset and a large, distributed collection of unlabeled data, while respecting data privacy.
Not ideal if all your data is centrally located and labeled, or if you don't have access to distributed, unlabeled datasets.
Stars
42
Forks
13
Language
Python
License
MIT
Category
Last pushed
Jul 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/diaoenmao/SemiFL-Semi-Supervised-Federated-Learning-for-Unlabeled-Clients-with-Alternate-Training"
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...