fairlearn

Fairness assessment tool

A tool to assess and mitigate unfairness in AI systems, helping developers ensure their models do not disproportionately harm certain groups of people.

A Python package to assess and improve fairness of machine learning models.

GitHub

2k stars
39 watching
425 forks
Language: Python
last commit: about 1 month ago
Linked from 4 awesome lists

aiai-systemsartificial-intelligencefairnessfairness-aifairness-assessmentfairness-mlgroup-fairnessharmsmachine-learningresponsible-aiunfairness-mitigation

Backlinks from these awesome lists:

Related projects:

Repository Description Stars
koaning/scikit-fairness A Python library providing tools and algorithms for fairness in machine learning model development 29
litian96/fair_flearn This project develops and evaluates algorithms for fair resource allocation in federated learning, aiming to promote more inclusive AI systems. 244
mbilalzafar/fair-classification Provides a Python implementation of fairness mechanisms in classification models to mitigate disparate impact and mistreatment. 190
google/ml-fairness-gym An open-source tool for simulating the long-term impacts of machine learning-based decision systems on social environments 314
algofairness/fairness-comparison An online repository providing benchmarking tools and data for evaluating fairness-aware machine learning algorithms 159
tensorflow/fairness-indicators An evaluation toolkit to assess fairness in machine learning models 343
zjelveh/learning-fair-representations An implementation of Zemel et al.'s 2013 algorithm for learning fair representations in machine learning 26
cgnorthcutt/cleanlab A tool for evaluating and improving the fairness of machine learning models 57
fair-chem/fairchem A collection of machine learning methods and tools for materials science and quantum chemistry. 929
taoqi98/fairvfl A collection of code implementing the FairVFL algorithm and its associated data structures and utilities for efficient and accurate fairness-aware machine learning model training. 7
ethicalml/xai An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance 1,135
adebayoj/fairml An auditing toolbox to assess the fairness of black-box predictive models 361
linkedin/lift A tool for measuring fairness and mitigating bias in machine learning workflows 167
dssg/aequitas Toolkit to audit and mitigate biases in machine learning models 701
modeloriented/fairmodels A tool for detecting bias in machine learning models and mitigating it using various techniques. 86