A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges

Abstract

The widespread adoption of Machine Learning systems, especially in more decision-critical applications such as criminal sentencing and bank loans, has led to increased concerns about fairness implications. Algorithms and metrics have been developed to mitigate and measure these discriminations. More recently, works have identified a more challenging form of bias called intersectional bias, which encompasses multiple sensitive attributes, such as race and gender, together. In this survey, we review the state-of-the-art in intersectional fairness. We present a taxonomy for intersectional notions of fairness and mitigation. Finally, we identify the key challenges and provide researchers with guidelines for future directions.

arXiv commentIJCAI 2023

References in corpus (17)

• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Fairness Without Demographics in Repeated Loss Minimization
• Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
• Compositional Fairness Constraints for Graph Embeddings
• Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation
• Online Learning with an Unknown Fairness Metric
• Towards Understanding Fairness and its Composition in Ensemble Machine Learning
• Fairness Testing: A Comprehensive Survey and Analysis of Trends
• Multiaccuracy: Black-Box Post-Processing for Fairness in Classification
• Auditing and Achieving Intersectional Fairness in Classification Problems
• On Learning Fairness and Accuracy on Multiple Subgroups
• Debiasing Word Embeddings with Nonlinear Geometry
• Intersectional Affirmative Action Policies for Top-k Candidates Selection
• Bayesian Modeling of Intersectional Fairness: The Variance of Bias
• Low-Degree Multicalibration

Cited by in corpus (7)

• Unmasking Gender Bias in Recommendation Systems and Enhancing Category-Aware Fairness
• NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers
• A Sequentially Fair Mechanism for Multiple Sensitive Attributes
• Evaluating the Social Impact of Generative AI Systems in Systems and Society
• Intersectionality and Testimonial Injustice in Medical Records
• Toward Substantive Intersectional Algorithmic Fairness: Desiderata for a Feminist Approach
• Bias Detection via Maximum Subgroup Discrepancy