Fairness Toolkits

Fairness toolkits are software packages designed to detect and mitigate bias in machine learning models, aiming to ensure equitable outcomes across different demographic groups. Current research focuses on developing more flexible and robust methods for defining and measuring fairness (e.g., using AUC gap and Equalized Odds), improving the integration of fairness considerations into existing machine learning workflows (e.g., through differentiable regularization terms), and addressing the challenges of real-world data limitations and dynamic fairness properties. These toolkits are crucial for promoting responsible AI development and deployment, impacting various fields by improving the fairness and trustworthiness of algorithms used in applications like hiring, loan applications, and education.

Papers

July 20, 2024

Implementing Fairness: the view from a FairDream
Thomas Souverain, Johnathan Nguyen, Nicolas Meric, Paul Égré
Best View AI Fairness Fairness Objective Achieving Fairness Equalized Odds Fairness Toolkits

July 3, 2024

FairJob: A Real-World Dataset for Fairness in Online Systems
Mariia Vladimirova, Federico Pavone, Eustache Diemert
Procedural Fairness Algorithmic Fairness Biased Datasets Real World Dataset Fairness Datasets Fairness Toolkits Fair Utility

May 23, 2024

Fairness Hub Technical Briefs: Definition and Detection of Distribution Shift
Nicolas Acevedo, Carmen Cortez, Chris Brooks, Rene Kizilcec, Renzhe Yu
Data Detection Distribution Shift Definition Defining Redefinition Machine Learning Task Prediction Task Fairness Toolkits Prediction Problem

October 26, 2023

fairret: a Framework for Differentiable Fairness Regularization Terms
Maarten Buyl, MaryBeth Defrance, Tijl De Bie
New Framework Procedural Fairness Fairness Regularization Fairness Toolkits

September 20, 2023

Fairness Hub Technical Briefs: AUC Gap
Jinsook Lee, Chris Brooks, Renzhe Yu, Rene Kizilcec
Absolute Stance Bias Model Bias Fairness Assessment AUC Metric Fairness Toolkits Intersectional Group

May 8, 2023

Runtime Monitoring of Dynamic Fairness Properties
Thomas A. Henzinger, Mahyar Karimi, Konstantin Kueffner, Kaushik Mallik
Procedural Fairness Runtime Monitoring Fairness Toolkits Dynamic Fairness

May 13, 2022

Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
Wesley Hanwen Deng, Manish Nagireddy, Michelle Seng Ah Lee, Jatinder Singh, Zhiwei Steven Wu, Kenneth Holstein, Haiyi Zhu
Machine Learning Practitioner ML Fairness Fairness Toolkits

February 19, 2022

The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness
Elizabeth Anne Watkins, Michael McKenna, Jiahao Chen
Algorithmic Fairness Responsible AI AI Ethic Cautionary TALE Metric Aware Abstraction Disparate Impact Fairness Toolkits

January 13, 2022

The Fairness Field Guide: Perspectives from Social and Formal Sciences
Alycia N. Carey, Xintao Wu
Machine Learning Machine Learning Model Procedural Fairness Synthesized View Fair Machine Learning Rigorous Framework Fairness Toolkits