akassharjun/ShapleyValueFL
A pip library for calculating the Shapley Value for computing the marginal contribution of each client in a Federated Learning environment.
This helps machine learning engineers or researchers working with federated learning environments to fairly assess the contribution of each client. You provide it with individual client models and methods for evaluation and aggregation. The output is a clear measure (Shapley Value) indicating how much each client contributes to the overall model's performance.
No commits in the last 6 months.
Use this if you need to fairly distribute rewards or understand the impact of individual data contributors in a federated learning setup.
Not ideal if your goal is not to measure individual client contributions within a federated learning system, or if you are working outside of machine learning.
Stars
29
Forks
3
Language
Python
License
MIT
Category
Last pushed
Dec 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/akassharjun/ShapleyValueFL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shap/shap
A game theoretic approach to explain the output of any machine learning model.
mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
iancovert/sage
For calculating global feature importance using Shapley values.
aerdem4/lofo-importance
Leave One Feature Out Importance
predict-idlab/powershap
A power-full Shapley feature selection method.