Fair-CMNB

Advancing Fairness-Aware Stream Learning with Naïve Bayes and Multi-Objective Optimization

verfasst von: Maryam Badar, Marco Fisichella
Abstract: Fairness-aware mining of data streams is a challenging concern in the contemporary domain of machine learning. Many stream learning algorithms are used to replace humans in critical decision-making processes, e.g., hiring staff, assessing credit risk, etc. This calls for handling massive amounts of incoming information with minimal response delay while ensuring fair and high-quality decisions. Although deep learning has achieved success in various domains, its computational complexity may hinder real-time processing, making traditional algorithms more suitable. In this context, we propose a novel adaptation of Naïve Bayes to mitigate discrimination embedded in the streams while maintaining high predictive performance through multi-objective optimization (MOO). Class imbalance is an inherent problem in discrimination-aware learning paradigms. To deal with class imbalance, we propose a dynamic instance weighting module that gives more importance to new instances and less importance to obsolete instances based on their membership in a minority or majority class. We have conducted experiments on a range of streaming and static datasets and concluded that our proposed methodology outperforms existing state-of-the-art (SoTA) fairness-aware methods in terms of both discrimination score and balanced accuracy.
Organisationseinheit(en): Forschungszentrum L3S
Typ: Artikel
Journal: Big Data and Cognitive Computing
Band: 8
Anzahl der Seiten: 20
Publikationsdatum: 31.01.2024
Publikationsstatus: Veröffentlicht
Peer-reviewed: Ja
ASJC Scopus Sachgebiete: Management-Informationssysteme, Information systems, Angewandte Informatik, Artificial intelligence
Elektronische Version(en): https://doi.org/10.3390/bdcc8020016 (Zugang: Offen)

BibTeX

@article{431b685660bf45e4ab76527ea8a07461,
title = "Fair-CMNB: Advancing Fairness-Aware Stream Learning with Na{\"i}ve Bayes and Multi-Objective Optimization",
abstract = "Fairness-aware mining of data streams is a challenging concern in the contemporary domain of machine learning. Many stream learning algorithms are used to replace humans in critical decision-making processes, e.g., hiring staff, assessing credit risk, etc. This calls for handling massive amounts of incoming information with minimal response delay while ensuring fair and high-quality decisions. Although deep learning has achieved success in various domains, its computational complexity may hinder real-time processing, making traditional algorithms more suitable. In this context, we propose a novel adaptation of Na{\"i}ve Bayes to mitigate discrimination embedded in the streams while maintaining high predictive performance through multi-objective optimization (MOO). Class imbalance is an inherent problem in discrimination-aware learning paradigms. To deal with class imbalance, we propose a dynamic instance weighting module that gives more importance to new instances and less importance to obsolete instances based on their membership in a minority or majority class. We have conducted experiments on a range of streaming and static datasets and concluded that our proposed methodology outperforms existing state-of-the-art (SoTA) fairness-aware methods in terms of both discrimination score and balanced accuracy.",
keywords = "class imbalance, discrimination-aware learning, multi-objective optimization, online learning",
author = "Maryam Badar and Marco Fisichella",
note = "Funding Information: This research was funded by the Lower Saxony Ministry of Science and Culture (Nieders{\"a}chsische Ministerium f{\"u}r Wissenschaft und Kultur). ",
year = "2024",
month = jan,
day = "31",
doi = "10.3390/bdcc8020016",
language = "English",
volume = "8",
journal = "Big Data and Cognitive Computing",
issn = "2504-2289",
publisher = "MDPI AG",
number = "2",
}