Uncover and mitigate bias in AI and data-driven systems with our curated selection of research tools and libraries. This page provides direct access to cutting-edge software designed to identify, analyze, and reduce bias in machine learning models, datasets, and decision-making processes.
Fairness-aware ML Tutorials
Jupyter Notebook
This tutorial series offers a hands-on guide to fairness-aware machine learning that targets beginners in Fair-ML.
FLAC
Method
Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
FairBranch
Method
Stepwise guidance to run the FairBranch model in vision and tabular setup.
SDFD
Dataset
The Stable Diffusion Face-image Dataset that captures a broad spectrum of facial diversity encompassing not only demographics and biometrics but also non-permanent traits like make-up, hairstyle, and accessories.
AskBias
Web application
Inject stakeholder feedback in the numerical evaluation of fairness
definitions written in basic fuzzy logic.
Visual Bias Mitigator (VB-Mitigator)
Framework
Empowers researchers in the field of bias mitigation in computer vision. This codebase provides a comprehensive environment where users can easily implement, run, and evaluate existing visual bias mitigation methods.