euphoria0-0/Active-Client-Selection-for-Communication-efficient-Federated-Learning

Active Client Selection for Federated Learning

42
/ 100
Emerging

This project helps machine learning engineers and researchers to experiment with different client selection strategies for Federated Learning. It takes in distributed datasets like Federated EMNIST, CelebA, or CIFAR100, and outputs performance metrics for various client selection algorithms. The primary users are those working on optimizing the communication efficiency of federated learning models.

No commits in the last 6 months.

Use this if you are developing or researching federated learning systems and need to compare how different client selection methods impact model training and communication overhead.

Not ideal if you are a beginner looking for a high-level API to implement a federated learning model without diving into client selection algorithms.

federated-learning distributed-machine-learning deep-learning-research model-optimization privacy-preserving-ml
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

50

Forks

14

Language

Python

License

MIT

Last pushed

Apr 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/euphoria0-0/Active-Client-Selection-for-Communication-efficient-Federated-Learning"

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