diwangs/asynchronous-federated-learning

Study of data imbalance and asynchronous aggregation algorithm on Federated Learning system (using PySyft)

32
/ 100
Emerging

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.

federated-learning machine-learning-research distributed-data-analysis model-evaluation privacy-preserving-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

63

Forks

11

Language

Python

License

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.