FairTrade

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

verfasst von: Maryam Badar, Sandipan Sikdar, Wolfgang Nejdl, Marco Fisichella
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.
Organisationseinheit(en): Forschungszentrum L3S
Typ: Konferenzaufsatz in Fachzeitschrift
Journal: Proceedings of the AAAI Conference on Artificial Intelligence
Band: 38
Seiten: 10962-10970
Anzahl der Seiten: 9
ISSN: 2159-5399
Publikationsdatum: 24.03.2024
Publikationsstatus: Veröffentlicht
Peer-reviewed: Ja
ASJC Scopus Sachgebiete: Artificial intelligence
Elektronische Version(en): https://doi.org/10.1609/aaai.v38i10.28971 (Zugang: Offen)

BibTeX

@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",
journal = "Proceedings of the AAAI Conference on Artificial Intelligence",
issn = "2159-5399",
publisher = "OJS/PKP",
number = "10",
}