FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Autoren

Organisationseinheiten

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)10962-10970
Seitenumfang9
FachzeitschriftProceedings of the AAAI Conference on Artificial Intelligence
Jahrgang38
Ausgabenummer10
PublikationsstatusVeröffentlicht - 24 März 2024
Veranstaltung38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Kanada
Dauer: 20 Feb. 202427 Feb. 2024

Abstract

As Federated Learning (FL) gains prominence in distributed machine learning applications, achieving fairness without compromising predictive performance becomes paramount. The data being gathered from distributed clients in an FL environment often leads to class imbalance. In such scenarios, balanced accuracy rather than accuracy is the true representation of model performance. However, most state-of-the-art fair FL methods report accuracy as the measure of performance, which can lead to misguided interpretations of the model’s effectiveness to mitigate discrimination. To the best of our knowledge, this work presents the first attempt towards achieving Pareto-optimal trade-offs between balanced accuracy and fairness in a federated environment (FairTrade). By utilizing multi-objective optimization, the framework negotiates the intricate balance between model’s balanced accuracy and fairness. The framework’s agnostic design adeptly accommodates both statistical and causal fairness notions, ensuring its adaptability across diverse FL contexts. We provide empirical evidence of our framework’s efficacy through extensive experiments on five real-world datasets and comparisons with six baselines. The empirical results underscore the potential of our framework in improving the trade-off between fairness and balanced accuracy in FL applications.

ASJC Scopus Sachgebiete

Zitieren

FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning. / Badar, Maryam; Sikdar, Sandipan; Nejdl, Wolfgang et al.
in: Proceedings of the AAAI Conference on Artificial Intelligence, Jahrgang 38, Nr. 10, 24.03.2024, S. 10962-10970.

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Badar, M, Sikdar, S, Nejdl, W & Fisichella, M 2024, 'FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning', Proceedings of the AAAI Conference on Artificial Intelligence, Jg. 38, Nr. 10, S. 10962-10970. https://doi.org/10.1609/aaai.v38i10.28971
Badar M, Sikdar S, Nejdl W, Fisichella M. FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2024 Mär 24;38(10):10962-10970. doi: 10.1609/aaai.v38i10.28971
Badar, Maryam ; Sikdar, Sandipan ; Nejdl, Wolfgang et al. / FairTrade : Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning. in: Proceedings of the AAAI Conference on Artificial Intelligence. 2024 ; Jahrgang 38, Nr. 10. S. 10962-10970.
Download
@article{2ac345892bbf4e84b8443e404047c454,
title = "FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning",
abstract = "As Federated Learning (FL) gains prominence in distributed machine learning applications, achieving fairness without compromising predictive performance becomes paramount. The data being gathered from distributed clients in an FL environment often leads to class imbalance. In such scenarios, balanced accuracy rather than accuracy is the true representation of model performance. However, most state-of-the-art fair FL methods report accuracy as the measure of performance, which can lead to misguided interpretations of the model{\textquoteright}s effectiveness to mitigate discrimination. To the best of our knowledge, this work presents the first attempt towards achieving Pareto-optimal trade-offs between balanced accuracy and fairness in a federated environment (FairTrade). By utilizing multi-objective optimization, the framework negotiates the intricate balance between model{\textquoteright}s balanced accuracy and fairness. The framework{\textquoteright}s agnostic design adeptly accommodates both statistical and causal fairness notions, ensuring its adaptability across diverse FL contexts. We provide empirical evidence of our framework{\textquoteright}s efficacy through extensive experiments on five real-world datasets and comparisons with six baselines. The empirical results underscore the potential of our framework in improving the trade-off between fairness and balanced accuracy in FL applications.",
author = "Maryam Badar and Sandipan Sikdar and Wolfgang Nejdl and Marco Fisichella",
note = "Funding Information: This research was partially funded by the European Commission through the xAIM project, agreement No. INEA/CEF/ICT/A2020/2276680.; 38th AAAI Conference on Artificial Intelligence, AAAI 2024 ; Conference date: 20-02-2024 Through 27-02-2024",
year = "2024",
month = mar,
day = "24",
doi = "10.1609/aaai.v38i10.28971",
language = "English",
volume = "38",
pages = "10962--10970",
number = "10",

}

Download

TY - JOUR

T1 - FairTrade

T2 - 38th AAAI Conference on Artificial Intelligence, AAAI 2024

AU - Badar, Maryam

AU - Sikdar, Sandipan

AU - Nejdl, Wolfgang

AU - Fisichella, Marco

N1 - Funding Information: This research was partially funded by the European Commission through the xAIM project, agreement No. INEA/CEF/ICT/A2020/2276680.

PY - 2024/3/24

Y1 - 2024/3/24

N2 - As Federated Learning (FL) gains prominence in distributed machine learning applications, achieving fairness without compromising predictive performance becomes paramount. The data being gathered from distributed clients in an FL environment often leads to class imbalance. In such scenarios, balanced accuracy rather than accuracy is the true representation of model performance. However, most state-of-the-art fair FL methods report accuracy as the measure of performance, which can lead to misguided interpretations of the model’s effectiveness to mitigate discrimination. To the best of our knowledge, this work presents the first attempt towards achieving Pareto-optimal trade-offs between balanced accuracy and fairness in a federated environment (FairTrade). By utilizing multi-objective optimization, the framework negotiates the intricate balance between model’s balanced accuracy and fairness. The framework’s agnostic design adeptly accommodates both statistical and causal fairness notions, ensuring its adaptability across diverse FL contexts. We provide empirical evidence of our framework’s efficacy through extensive experiments on five real-world datasets and comparisons with six baselines. The empirical results underscore the potential of our framework in improving the trade-off between fairness and balanced accuracy in FL applications.

AB - As Federated Learning (FL) gains prominence in distributed machine learning applications, achieving fairness without compromising predictive performance becomes paramount. The data being gathered from distributed clients in an FL environment often leads to class imbalance. In such scenarios, balanced accuracy rather than accuracy is the true representation of model performance. However, most state-of-the-art fair FL methods report accuracy as the measure of performance, which can lead to misguided interpretations of the model’s effectiveness to mitigate discrimination. To the best of our knowledge, this work presents the first attempt towards achieving Pareto-optimal trade-offs between balanced accuracy and fairness in a federated environment (FairTrade). By utilizing multi-objective optimization, the framework negotiates the intricate balance between model’s balanced accuracy and fairness. The framework’s agnostic design adeptly accommodates both statistical and causal fairness notions, ensuring its adaptability across diverse FL contexts. We provide empirical evidence of our framework’s efficacy through extensive experiments on five real-world datasets and comparisons with six baselines. The empirical results underscore the potential of our framework in improving the trade-off between fairness and balanced accuracy in FL applications.

UR - http://www.scopus.com/inward/record.url?scp=85189754417&partnerID=8YFLogxK

U2 - 10.1609/aaai.v38i10.28971

DO - 10.1609/aaai.v38i10.28971

M3 - Conference article

AN - SCOPUS:85189754417

VL - 38

SP - 10962

EP - 10970

JO - Proceedings of the AAAI Conference on Artificial Intelligence

JF - Proceedings of the AAAI Conference on Artificial Intelligence

SN - 2159-5399

IS - 10

Y2 - 20 February 2024 through 27 February 2024

ER -

Von denselben Autoren