Demystifying the Optimal Fair Classifier in Multi-Class Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Li, Li, Yuyuan, Feng, XiaoHua, Zhang, Jiaming, Yu, Fengyuan, Chen, Chaochao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911735816912896
author Zhang, Li
Li, Yuyuan
Feng, XiaoHua
Zhang, Jiaming
Yu, Fengyuan
Chen, Chaochao
author_facet Zhang, Li
Li, Yuyuan
Feng, XiaoHua
Zhang, Jiaming
Yu, Fengyuan
Chen, Chaochao
contents Ensuring fair and equitable treatment across diverse groups, particularly in multi-class classification tasks, poses a significant challenge due to the persistent biases inherent in machine learning models. Most existing bias mitigation techniques are tailored to binary settings, and the presence of multi-dimensional outputs and complex fairness mechanisms makes their extension to multi-class scenarios neither straightforward nor effective. In this paper, we investigate two fundamental, unresolved challenges in fair classification: (i) characterizing the optimal accuracy-fairness frontier in multi-class settings, and (ii) designing practical algorithms that attain this optimum in different training phases. To tackle these challenges, we first specify an analytically tractable probabilistic formulation of the optimal classifier under fairness constraints. Building upon this, we propose two attribute-blind algorithms to enforce fairness requirements in practice: an in-processing approach for fairness intervention during training via the reduction approach, and a post-processing approach for fine-tuning output probabilities with plug-in estimation. Theoretical analysis reveals that both methods converge to the optimal accuracy-fairness Pareto frontier. Experiments conducted on multiple datasets demonstrate the superior performance of our methods in balancing accuracy and fairness.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00656
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Demystifying the Optimal Fair Classifier in Multi-Class Classification
Zhang, Li
Li, Yuyuan
Feng, XiaoHua
Zhang, Jiaming
Yu, Fengyuan
Chen, Chaochao
Machine Learning
Artificial Intelligence
Ensuring fair and equitable treatment across diverse groups, particularly in multi-class classification tasks, poses a significant challenge due to the persistent biases inherent in machine learning models. Most existing bias mitigation techniques are tailored to binary settings, and the presence of multi-dimensional outputs and complex fairness mechanisms makes their extension to multi-class scenarios neither straightforward nor effective. In this paper, we investigate two fundamental, unresolved challenges in fair classification: (i) characterizing the optimal accuracy-fairness frontier in multi-class settings, and (ii) designing practical algorithms that attain this optimum in different training phases. To tackle these challenges, we first specify an analytically tractable probabilistic formulation of the optimal classifier under fairness constraints. Building upon this, we propose two attribute-blind algorithms to enforce fairness requirements in practice: an in-processing approach for fairness intervention during training via the reduction approach, and a post-processing approach for fine-tuning output probabilities with plug-in estimation. Theoretical analysis reveals that both methods converge to the optimal accuracy-fairness Pareto frontier. Experiments conducted on multiple datasets demonstrate the superior performance of our methods in balancing accuracy and fairness.
title Demystifying the Optimal Fair Classifier in Multi-Class Classification
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2606.00656