euphoria0-0/Active-Client-Selection-for-Communication-efficient-Federated-Learning
Active Client Selection for Federated Learning
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.
Stars
50
Forks
14
Language
Python
License
MIT
Category
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.
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...