paper-with-me

Papers

FairTree: Subgroup Fairness Auditing of Machine Learning Models with Bias-Variance Decomposition

2026-04-21 · Rudolf Debelak arxiv

The evaluation of machine learning models typically relies mainly on performance metrics based on loss functions, which risk to overlook changes in performance in relevant subgroups. Auditing tools such as SliceFinder and SliceLine were proposed to detect such groups, but usually have conceptual disadvantages, such as the inability to directly address continuous covariates. In this paper, we introduce FairTree, a novel algorithm adapted from psychometric invariance testing. Unlike SliceFinder and related algorithms, FairTree directly handles continuous, categorical, and ordinal features without discretization. It further decomposes performance disparities into systematic bias and variance, allowing a categorization of changes in algorithm performance. We propose and evaluate two variations of the algorithm: a permutation-based approach, which is conceptually closer to SliceFinder, and a fluctuation test. Through simulation studies that include a direct comparison with SliceLine, we demonstrate that both approaches have a satisfactory rate of false-positive results, but that the fluctuation approach has relatively higher power. We further illustrate the method on the UCI Adult Census dataset. The proposed algorithms provide a flexible framework for the statistical evaluation of the performance and aspects of fairness of machine learning models in a wide range of applications even in relatively small data.

📄 PDF Abstract BibTeX arXiv:2604.19357

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FALE: Fairness-Aware ALE Plots for Auditing Bias in Subgroups

2024-04-29 · Giorgos Giannopoulos, Dimitris Sacharidis, Nikolas Theologitis, Loukas Kavouras 외

Fairness is steadily becoming a crucial requirement of Machine Learning (ML) systems. A particularly important notion is subgroup fairness, i.e., fairness in subgroups of individuals that are defined by more than one att…

AttributeFairness

Auditing Predictive Models for Intersectional Biases

2023-06-22 · Kate S. Boxer, Edward McFowland III, Daniel B. Neill

Predictive models that satisfy group fairness criteria in aggregate for members of a protected class, but do not guarantee subgroup fairness, could produce biased predictions for individuals at the intersection of two or…

Bias DetectionFairness

Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN

2022-11-16 · Anaelia Ovalle, Sunipa Dev, Jieyu Zhao, Majid Sarrafzadeh 외

Auditing machine learning-based (ML) healthcare tools for bias is critical to preventing patient harm, especially in communities that disproportionately face health inequities. General frameworks are becoming increasingl…

Bias DetectionClusteringFairness

Distribution-Specific Auditing For Subgroup Fairness

2024-01-27 · Daniel Hsu, Jizhou Huang, Brendan Juba

We study the problem of auditing classifiers with the notion of statistical subgroup fairness. Kearns et al. (2018) has shown that the problem of auditing combinatorial subgroups fairness is as hard as agnostic learning.…

Fairness

Evaluating Intersectional Fairness across Clinical Machine Learning Use Cases using Fairlogue and the All of Us Research Program

2026-04-07 · Nick Souligne, Vignesh Subbian arxiv

Intersectional biases in healthcare data can produce compound disparities in clinical machine learning models, yet most fairness evaluations assess demographic attributes independently. FairLogue, a toolkit for intersect…