Intersectional Fairness

Intersectional fairness in machine learning addresses the challenge of algorithmic bias affecting individuals based on overlapping sensitive attributes (e.g., race and gender), going beyond single-attribute fairness considerations. Current research focuses on developing methods for detecting and mitigating such biases, employing techniques like data augmentation tailored to hierarchical group structures, fairness-aware generative models, and multi-task learning to transfer fairness across datasets with limited demographic information. This work is crucial for ensuring equitable outcomes in AI applications across various domains, from healthcare and education to hiring and loan applications, and is driving the development of new fairness metrics and algorithms that account for the complex interplay of multiple protected characteristics.

Papers

May 31, 2024

Intersectional Unfairness Discovery
Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui
Generative Model Intersectional Bias Intersectional Fairness

May 23, 2024

Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure
Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller
Synthetic Data Generation Diverse Datasets Intersectional Fairness Data Augmentation Approach Group Structure

April 25, 2024

Conditional Fairness for Generative AIs
Chih-Hong Cheng, Harald Ruess, Changshun Wu, Xingyu Zhao
Generative AI Procedural Fairness Direct Assessment Generative AI Model Formal Specification Proportional Fairness Intersectional Fairness Exact Enforcement Current Generative AI

March 27, 2024

Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities
Dana Moukheiber, Saurabh Mahindre, Lama Moukheiber, Mira Moukheiber, Mingchen Gao
High Dimensional Multi Label Classification Fairness Constraint Empirical Analysis Medical Information Mart for Intensive Balanced Dataset Social Determinant Intersectional Fairness Multi Label Chest X Ray Health Equity

February 5, 2024

Intersectional Two-sided Fairness in Recommendation
Yifan Wang, Peijie Sun, Weizhi Ma, Min Zhang, Yuan Zhang, Peng Jiang, Shaoping Ma
Effective Recommendation Intersectional Fairness User Oriented Fairness Fairness Aware Recommendation

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

June 20, 2023

Intersectionality and Testimonial Injustice in Medical Records
Kenya S. Andrews, Bhuvani Shah, Lu Cheng
Clinical Note Fairness Metric Intersectional Social Attribute Intersectional Fairness Subgroup Fairness

May 22, 2023

Transferring Fairness using Multi-Task Learning with Limited Demographic Information
Carlos Aguirre, Mark Dredze
Multi Task Learning Fairness Loss Intersectional Fairness Demographic Fairness

May 21, 2023

Fair Without Leveling Down: A New Intersectional Fairness Definition
Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller
Different Level Proportional Fairness Intersectional Fairness

May 11, 2023

A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges
Usman Gohar, Lu Cheng
Machine Learning Timely Survey Technical Challenge Procedural Fairness Intersectional Bias Fairness Implication Intersectional Fairness Intersectional Social Attribute

May 1, 2023

Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity
Josh Gardner, Renzhe Yu, Quan Nguyen, Christopher Brooks, Rene Kizilcec
Procedural Fairness Model Performance Future Implication Model Fairness Zero Shot Transfer Intersectional Fairness Teaching Model

February 24, 2023

Intersectional Fairness: A Fractal Approach
Giulio Filippi, Sara Zannone, Adriano Koshiyama
Artificial Intelligence Procedural Fairness Fair AI Intersectional Bias Intersectional Fairness Multifractal Analysis

July 20, 2022

MANI-Rank: Multiple Attribute and Intersectional Group Fairness for Consensus Ranking
Kathleen Cachel, Elke Rundensteiner, Lane Harrison
Group Fairness Multiple Attribute Intersectional Fairness Consensus Ranking Proportional Ranking Fairness Attribute

June 12, 2022

Bounding and Approximating Intersectional Fairness through Marginal Fairness
Mathieu Molina, Patrick Loiseau
General Bound Proportional Fairness Intersectional Fairness

May 5, 2022

Subverting Fair Image Search with Generative Adversarial Perturbations
Avijit Ghosh, Matthew Jagielski, Christo Wilson
Native Robustness Fair Machine Learning Intersectional Fairness

May 2, 2022

A Novel Approach to Fairness in Automated Decision-Making using Affective Normalization
Jesse Hoey, Gabrielle Chan
Procedural Fairness Decision Making Novel Approach Target Emotion Intersectional Fairness Sentiment Bias