The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).

This package can be used for dominance analysis or Shapley Value Regression for finding relative importance of predictors on given dataset. This library can be used for key driver analysis or marginal resource allocation models.

pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation

This repo is the implementation of paper ''SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning''.

Measuring data importance over ML pipelines using the Shapley value.

A pip library for calculating the Shapley Value for computing the marginal contribution of each client in a Federated Learning environment.

PyTorch reimplementation of computing Shapley values via Truncated Monte Carlo sampling from "What is your data worth? Equitable Valuation of Data" by Amirata Ghorbani and James Zou [ICML 2019]

Profit Allocation for Federated Learning

Hopefully, a compact and general-purpose Python package for Multiperturbation Shapley value Analysis (MSA).

A methodology designed to measure the contribution of the features to the predictive performance of any econometric or machine learning model.

This is the official source code for CVPR 2024 paper [WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts]

Codebase for "Greedy Shapley Client Selection for Communication-Efficient Federated Learning"

LINe: Out-of-Distribution Detection by Leveraging Important Neurons (CVPR 2023)

Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation (ACL 2020)

Interpretable machine learning based on Shapley values

HERALD: An Annotation Efficient Method to Train User Engagement Predictors in Dialogs (ACL 2021)

Applying GradCAM method with 3 kinds of CNN-based model for NLP classification task on french dataset.

Explain model and feature dependencies by decomposition of SHAP values

Two Group Recommendation Approaches based on the Contribution of the Users and Pairwise Preferences

Set of algorithms from System theory and analysis course