When mitigating bias is unfair: multiplicity and arbitrariness in algorithmic group fairness
Most research on fair machine learning has prioritized optimizing criteria such as Demographic Parity and Equalized Odds. Despite these efforts, there remains a limited understanding of how different bias mitigation strategies affect individual predictions and whether they introduce arbitrariness into the debiasing process. This paper addresses these gaps by exploring whether models that achieve comparable fairness and accuracy metrics impact the same individuals and mitigate bias in a consistent manner. We introduce the FRAME (FaiRness Arbitrariness and Multiplicity Evaluation) framework, which evaluates bias mitigation through five dimensions: Impact Size (how many people were affected), Change Direction (positive versus negative changes), Decision Rates (impact on models' acceptance rates), Affected Subpopulations (who was affected), and Neglected Subpopulations (where unfairness persists). This framework is intended to help practitioners understand the impacts of debiasing processes and make better-informed decisions regarding model selection. Applying FRAME to various bias mitigation approaches across key datasets allows us to exhibit significant differences in the behaviors of debiasing methods. These findings highlight the limitations of current fairness criteria and the inherent arbitrariness in the debiasing process.
Code (1)
Tasks
FairnessModel SelectionSimilar Papers 제목 키워드 기반
The Curious Case of Arbitrariness in Machine Learning
Algorithmic modelling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has recentl…
The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity
Model multiplicity, the phenomenon where multiple models achieve similar performance despite different underlying learned functions, introduces arbitrariness in model selection. While this arbitrariness may seem inconseq…
Model SelectionMitigating the Multiplicity Burden: The Role of Calibration in Reducing Predictive Multiplicity of Classifiers
As machine learning models are increasingly deployed in high-stakes environments, ensuring both probabilistic reliability and prediction stability has become critical. This paper examines the interplay between classifica…
Arbitrariness Lies Beyond the Fairness-Accuracy Frontier
Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predictive multiplicity. We demonstrate that fai…
Decision MakingFairnessIndividual Arbitrariness and Group Fairness
Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples---a phenomenon known as predictive multiplicity. We demonstrate that fair…