Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rule

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Xuan, Broelemann, Klaus, Ruggieri, Salvatore, Kasneci, Gjergji
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909331183632384
author Zhao, Xuan
Broelemann, Klaus
Ruggieri, Salvatore
Kasneci, Gjergji
author_facet Zhao, Xuan
Broelemann, Klaus
Ruggieri, Salvatore
Kasneci, Gjergji
contents We introduce an innovative approach to enhancing the empirical risk minimization (ERM) process in model training through a refined reweighting scheme of the training data to enhance fairness. This scheme aims to uphold the sufficiency rule in fairness by ensuring that optimal predictors maintain consistency across diverse sub-groups. We employ a bilevel formulation to address this challenge, wherein we explore sample reweighting strategies. Unlike conventional methods that hinge on model size, our formulation bases generalization complexity on the space of sample weights. We discretize the weights to improve training speed. Empirical validation of our method showcases its effectiveness and robustness, revealing a consistent improvement in the balance between prediction performance and fairness metrics across various experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2408_14126
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rule
Zhao, Xuan
Broelemann, Klaus
Ruggieri, Salvatore
Kasneci, Gjergji
Machine Learning
Computers and Society
We introduce an innovative approach to enhancing the empirical risk minimization (ERM) process in model training through a refined reweighting scheme of the training data to enhance fairness. This scheme aims to uphold the sufficiency rule in fairness by ensuring that optimal predictors maintain consistency across diverse sub-groups. We employ a bilevel formulation to address this challenge, wherein we explore sample reweighting strategies. Unlike conventional methods that hinge on model size, our formulation bases generalization complexity on the space of sample weights. We discretize the weights to improve training speed. Empirical validation of our method showcases its effectiveness and robustness, revealing a consistent improvement in the balance between prediction performance and fairness metrics across various experiments.
title Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rule
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2408.14126