Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | 84 |
| Fachzeitschrift | Data Mining and Knowledge Discovery |
| Jahrgang | 39 |
| Ausgabenummer | 6 |
| Frühes Online-Datum | 17 Sept. 2025 |
| Publikationsstatus | Veröffentlicht - 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
- Informatik (insg.)
- Information systems
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Computernetzwerke und -kommunikation
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Data Mining and Knowledge Discovery, Jahrgang 39, Nr. 6, 84, 11.2025.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
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 -