Fed-FUEL: fairness and utility enhancing agnostic federated learning framework

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

Organisationseinheiten

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer84
FachzeitschriftData Mining and Knowledge Discovery
Jahrgang39
Ausgabenummer6
Frühes Online-Datum17 Sept. 2025
PublikationsstatusVeröffentlicht - Nov. 2025

Abstract

Federated learning (FL) is an emerging communication-efficient and collaborative learning paradigm of machine learning with privacy guarantees. As these advancements unfold, adapting FL for fairness-aware learning becomes crucial. In this context, we propose a pre-processing fairness and utility (balanced accuracy) enhancing agnostic federated learning framework (Fed-FUEL) that mitigates discrimination embedded in the non-independent identically distributed data. We contribute a novel adaptive data manipulation method that mitigates discrimination embedded in the data at client side during optimization, resulting in an optimized and fair centralized server. This pre-processing approach abstracts the model architecture from the equation, offering a significant advantage in a federated environment. This abstraction not only facilitates a broader application across diverse model architectures without necessitating modifications but also sidesteps the potential complexities and inefficiencies associated with model-specific in-processing methods. Extensive experiments with a range of publicly available datasets demonstrate that our method outperforms the competing baselines in terms of both discrimination mitigation and predictive performance. Our model effectively adapts to both statistical and causal fairness notions, as shown through our experiments.

ASJC Scopus Sachgebiete

Zitieren

Fed-FUEL: fairness and utility enhancing agnostic federated learning framework. / Badar, Maryam; Younis, Raneen; Sikdar, Sandipan et al.
in: Data Mining and Knowledge Discovery, Jahrgang 39, Nr. 6, 84, 11.2025.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Badar M, Younis R, Sikdar S, Nejdl W, Fisichella M. Fed-FUEL: fairness and utility enhancing agnostic federated learning framework. Data Mining and Knowledge Discovery. 2025 Nov;39(6):84. Epub 2025 Sep 17. doi: 10.1007/s10618-025-01152-0
Badar, Maryam ; Younis, Raneen ; Sikdar, Sandipan et al. / Fed-FUEL : fairness and utility enhancing agnostic federated learning framework. in: Data Mining and Knowledge Discovery. 2025 ; Jahrgang 39, Nr. 6.
Download
@article{4aade4a873b146bcbd73030acd7a0ad7,
title = "Fed-FUEL: fairness and utility enhancing agnostic federated learning framework",
abstract = "Federated learning (FL) is an emerging communication-efficient and collaborative learning paradigm of machine learning with privacy guarantees. As these advancements unfold, adapting FL for fairness-aware learning becomes crucial. In this context, we propose a pre-processing fairness and utility (balanced accuracy) enhancing agnostic federated learning framework (Fed-FUEL) that mitigates discrimination embedded in the non-independent identically distributed data. We contribute a novel adaptive data manipulation method that mitigates discrimination embedded in the data at client side during optimization, resulting in an optimized and fair centralized server. This pre-processing approach abstracts the model architecture from the equation, offering a significant advantage in a federated environment. This abstraction not only facilitates a broader application across diverse model architectures without necessitating modifications but also sidesteps the potential complexities and inefficiencies associated with model-specific in-processing methods. Extensive experiments with a range of publicly available datasets demonstrate that our method outperforms the competing baselines in terms of both discrimination mitigation and predictive performance. Our model effectively adapts to both statistical and causal fairness notions, as shown through our experiments.",
keywords = "Causality, Class imbalance, Fairness, Federated learning, Privacy",
author = "Maryam Badar and Raneen Younis and Sandipan Sikdar and Wolfgang Nejdl and Marco Fisichella",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",
year = "2025",
month = nov,
doi = "10.1007/s10618-025-01152-0",
language = "English",
volume = "39",
journal = "Data Mining and Knowledge Discovery",
issn = "1384-5810",
publisher = "Springer Netherlands",
number = "6",

}

Download

TY - JOUR

T1 - Fed-FUEL

T2 - fairness and utility enhancing agnostic federated learning framework

AU - Badar, Maryam

AU - Younis, Raneen

AU - Sikdar, Sandipan

AU - Nejdl, Wolfgang

AU - Fisichella, Marco

N1 - Publisher Copyright: © The Author(s) 2025.

PY - 2025/11

Y1 - 2025/11

N2 - Federated learning (FL) is an emerging communication-efficient and collaborative learning paradigm of machine learning with privacy guarantees. As these advancements unfold, adapting FL for fairness-aware learning becomes crucial. In this context, we propose a pre-processing fairness and utility (balanced accuracy) enhancing agnostic federated learning framework (Fed-FUEL) that mitigates discrimination embedded in the non-independent identically distributed data. We contribute a novel adaptive data manipulation method that mitigates discrimination embedded in the data at client side during optimization, resulting in an optimized and fair centralized server. This pre-processing approach abstracts the model architecture from the equation, offering a significant advantage in a federated environment. This abstraction not only facilitates a broader application across diverse model architectures without necessitating modifications but also sidesteps the potential complexities and inefficiencies associated with model-specific in-processing methods. Extensive experiments with a range of publicly available datasets demonstrate that our method outperforms the competing baselines in terms of both discrimination mitigation and predictive performance. Our model effectively adapts to both statistical and causal fairness notions, as shown through our experiments.

AB - Federated learning (FL) is an emerging communication-efficient and collaborative learning paradigm of machine learning with privacy guarantees. As these advancements unfold, adapting FL for fairness-aware learning becomes crucial. In this context, we propose a pre-processing fairness and utility (balanced accuracy) enhancing agnostic federated learning framework (Fed-FUEL) that mitigates discrimination embedded in the non-independent identically distributed data. We contribute a novel adaptive data manipulation method that mitigates discrimination embedded in the data at client side during optimization, resulting in an optimized and fair centralized server. This pre-processing approach abstracts the model architecture from the equation, offering a significant advantage in a federated environment. This abstraction not only facilitates a broader application across diverse model architectures without necessitating modifications but also sidesteps the potential complexities and inefficiencies associated with model-specific in-processing methods. Extensive experiments with a range of publicly available datasets demonstrate that our method outperforms the competing baselines in terms of both discrimination mitigation and predictive performance. Our model effectively adapts to both statistical and causal fairness notions, as shown through our experiments.

KW - Causality

KW - Class imbalance

KW - Fairness

KW - Federated learning

KW - Privacy

UR - http://www.scopus.com/inward/record.url?scp=105016609471&partnerID=8YFLogxK

U2 - 10.1007/s10618-025-01152-0

DO - 10.1007/s10618-025-01152-0

M3 - Article

AN - SCOPUS:105016609471

VL - 39

JO - Data Mining and Knowledge Discovery

JF - Data Mining and Knowledge Discovery

SN - 1384-5810

IS - 6

M1 - 84

ER -

Von denselben Autoren