clickade/federated-shapley-playground
Playground for testing Horizontal Federated Machine Learning systems using the Shapley Value for profit allocation
This system helps researchers and machine learning practitioners evaluate how different participants contribute to a federated learning model. You provide datasets like MNIST or EMNIST, specify neural network sizes, and define how clients behave. The system then outputs performance metrics, Shapley Value rewards for each participant, and training timings. It's designed for those investigating fair profit allocation in collaborative AI projects.
No commits in the last 6 months.
Use this if you need to test and understand how individual participants in a horizontal federated learning system contribute to the overall model's performance and how rewards can be allocated.
Not ideal if you are looking for a production-ready federated learning framework or a tool for general-purpose machine learning model training.
Stars
9
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/clickade/federated-shapley-playground"
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...