diwangs/asynchronous-federated-learning
Study of data imbalance and asynchronous aggregation algorithm on Federated Learning system (using PySyft)
This project helps researchers and machine learning practitioners understand how data distribution and timing differences between data sources impact the performance of privacy-preserving machine learning models. It takes in a dataset that can be distributed across multiple clients and simulates different training speeds to analyze how these factors affect the final model's accuracy. The primary users are researchers or engineers exploring the nuances of federated learning in real-world, decentralized environments.
No commits in the last 6 months.
Use this if you are a researcher or practitioner studying how data imbalance and unsynchronized training rounds affect federated learning model performance, especially in scenarios where data sources operate at different speeds.
Not ideal if you are looking for a production-ready federated learning framework or a tool to deploy privacy-preserving models directly.
Stars
63
Forks
11
Language
Python
License
—
Category
Last pushed
Oct 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/diwangs/asynchronous-federated-learning"
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
zama-ai/concrete-ml
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on...
anupamkliv/FedERA
FedERA is a modular and fully customizable open-source FL framework, aiming to address these...
p2pfl/p2pfl
P2PFL is a decentralized federated learning library that enables federated learning on...