Explainability and Fairness

Aequitas is an open-source bias audit toolkit designed to evaluate machine learning models for discrimination and fairne...

AI Explainability 360 is an open-source toolkit that provides a comprehensive set of algorithms and metrics to interpret...

AI Fairness 360 (AIF360) is an open-source toolkit that provides a suite of fairness metrics, bias detection algorithms,...

Alibi is an open-source Python library designed for interpreting and explaining machine learning models, with a focus on...

Captum is a model interpretability library for PyTorch that provides tools to understand and debug deep learning models....

Fairlearn is a Python toolkit designed to help developers assess and mitigate unfairness in machine learning models. It ...

InterpretML is an open-source toolkit that enables users to train interpretable machine learning models (like decision t...

Lightly is a Python framework for self-supervised learning on image data, enabling users to train models without labeled...

LOFO Importance is a Python library that evaluates feature importance for machine learning models by iteratively excludi...

mljar-supervised is an AutoML Python package designed for tabular data, automating tasks like feature engineering, hyper...

Quantus is an open-source toolkit designed to evaluate and benchmark explanation methods for neural networks, focusing o...

SHAP (SHapley Additive exPlanations) is a Python library that provides interpretable explanations for machine learning m...

SHAPash is a Python library that simplifies the interpretation of machine learning models by generating interactive visu...

WhatIf is an interactive visualization tool designed to analyze machine learning models, enabling users to explore model...