Understanding trade-offs in classifier bias with quality-diversity optimization: an application to talent management

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jaramillo, Catalina M, Squires, Paul, Togelius, Julian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909611574951936
author Jaramillo, Catalina M
Squires, Paul
Togelius, Julian
author_facet Jaramillo, Catalina M
Squires, Paul
Togelius, Julian
contents Fairness,the impartial treatment towards individuals or groups regardless of their inherent or acquired characteristics [20], is a critical challenge for the successful implementation of Artificial Intelligence (AI) in multiple fields like finances, human capital, and housing. A major struggle for the development of fair AI models lies in the bias implicit in the data available to train such models. Filtering or sampling the dataset before training can help ameliorate model bias but can also reduce model performance and the bias impact can be opaque. In this paper, we propose a method for visualizing the biases inherent in a dataset and understanding the potential trade-offs between fairness and accuracy. Our method builds on quality-diversity optimization, in particular Covariance Matrix Adaptation Multi-dimensional Archive of Phenotypic Elites (MAP-Elites). Our method provides a visual representation of bias in models, allows users to identify models within a minimal threshold of fairness, and determines the trade-off between fairness and accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16965
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Understanding trade-offs in classifier bias with quality-diversity optimization: an application to talent management
Jaramillo, Catalina M
Squires, Paul
Togelius, Julian
Neural and Evolutionary Computing
Fairness,the impartial treatment towards individuals or groups regardless of their inherent or acquired characteristics [20], is a critical challenge for the successful implementation of Artificial Intelligence (AI) in multiple fields like finances, human capital, and housing. A major struggle for the development of fair AI models lies in the bias implicit in the data available to train such models. Filtering or sampling the dataset before training can help ameliorate model bias but can also reduce model performance and the bias impact can be opaque. In this paper, we propose a method for visualizing the biases inherent in a dataset and understanding the potential trade-offs between fairness and accuracy. Our method builds on quality-diversity optimization, in particular Covariance Matrix Adaptation Multi-dimensional Archive of Phenotypic Elites (MAP-Elites). Our method provides a visual representation of bias in models, allows users to identify models within a minimal threshold of fairness, and determines the trade-off between fairness and accuracy.
title Understanding trade-offs in classifier bias with quality-diversity optimization: an application to talent management
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2411.16965