Group Fairness Metric

Group fairness metrics aim to quantify and mitigate bias in machine learning models, ensuring fair outcomes across different demographic groups. Current research focuses on developing new metrics that incorporate domain expertise and address limitations of existing approaches like demographic parity and equalized odds, including exploring causal connections between fairness and accuracy. This work is crucial for building trustworthy AI systems, impacting both the development of fairer algorithms and the ethical deployment of machine learning in high-stakes applications such as loan applications, hiring processes, and healthcare. Ongoing efforts also involve analyzing the influence of individual features on bias and developing methods to protect sensitive attributes during fairness assessments.

Papers

October 17, 2024

The Disparate Benefits of Deep Ensembles
Kajetan Schweighofer, Adrian Arnaiz-Rodriguez, Sepp Hochreiter, Nuria Oliver
Algorithmic Fairness Deep Ensemble Disparate Impact Group Fairness Metric

June 12, 2024

Underneath the Numbers: Quantitative and Qualitative Gender Fairness in LLMs for Depression Prediction
Micol Spitale, Jiaee Cheong, Hatice Gunes
Medical LLM Gender Bias Depression Detection Bias Evaluation Quantitative Explanation Group Fairness Metric Gender Fairness

October 31, 2023

Parametric Fairness with Statistical Guarantees
François HU, Philipp Ratz, Arthur Charpentier
Statistical Guarantee Equalized Odds Fairness Criterion Intersectional Fairness Group Fairness Metric

October 30, 2023

Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness
Jacy Reese Anthis, Victor Veitch
Group Fairness Counterfactual Fairness Robust Prediction Fair Predictor Group Fairness Metric

March 1, 2023

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization
Sangwon Jung, Taeeon Park, Sanghyuk Chun, Taesup Moon
Robust Optimization Group Fairness Fairness Metric Fairness Accuracy Fairness Regularization Fairness Aware Training Group Fairness Metric

December 29, 2022

Properties of Group Fairness Metrics for Rankings
Tobias Schumacher, Marlene Lutz, Sandipan Sikdar, Markus Strohmaier
Procedural Fairness Group Fairness Partial Ranking Many Property Fair Ranking Group Fairness Metric

November 3, 2022

Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
Faisal Hamman, Jiahao Chen, Sanghamitra Dutta
Differential Privacy Privacy Policy Algorithmic Fairness Fairness Metric Fairness Assessment Group Fairness Metric Attribute Leakage

June 6, 2022

Distributive Justice as the Foundational Premise of Fair ML: Unification, Extension, and Interpretation of Group Fairness Metrics
Joachim Baumann, Corinna Hertweck, Michele Loi, Christoph Heitz
Fairness Metric Fair Machine Learning Flawed Foundation Anti Unification Fairness Objective Group Fairness Metric

June 1, 2022

How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis
Bishwamittra Ghosh, Debabrota Basu, Kuldeep S. Meel
Feature Wise Fairness Intervention Biased Classifier Global Sensitivity Analysis Group Fairness Metric Fairness Influence Function

Group Fairness Metric

Papers

The Disparate Benefits of Deep Ensembles

Underneath the Numbers: Quantitative and Qualitative Gender Fairness in LLMs for Depression Prediction

Parametric Fairness with Statistical Guarantees

Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

Properties of Group Fairness Metrics for Rankings

Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity

Distributive Justice as the Foundational Premise of Fair ML: Unification, Extension, and Interpretation of Group Fairness Metrics

How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis