chenxingqiang/PFLoRA-lib

PFLoRA-lib: Personalized Federated Learning with LoRA Algorithm Library focusing on privacy-protection, federated-learning, Citation, Extensibility, Supported A

21
/ 100
Experimental

This library helps machine learning researchers evaluate and compare different federated learning algorithms, especially those that personalize models while protecting data privacy. It takes various datasets (like medical images or text) and different federated learning algorithms as input, producing performance metrics and insights into how well models learn collaboratively without sharing raw data. Researchers and data scientists working on distributed machine learning problems in sensitive domains would find this useful.

No commits in the last 6 months.

Use this if you are a researcher or data scientist evaluating personalized federated learning algorithms and need a robust platform for testing and comparing their performance with an emphasis on privacy and efficiency.

Not ideal if you need a production-ready federated learning system for deploying models directly to edge devices or a simple tool for basic centralized machine learning tasks.

federated-learning privacy-preserving-ai distributed-machine-learning machine-learning-research model-personalization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

GPL-2.0

Last pushed

Sep 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/chenxingqiang/PFLoRA-lib"

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