Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ

Marika Kaden; Alexander Engelsberger; Ronny Schubert; Sofie Lövdal; Elina van den Brandhof; Michael Biehl; Thomas Villmann

doi:10.14428/esann/2025.ES2025-65

Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ

Marika Kaden
, Alexander Engelsberger
, Ronny Schubert
, Sofie Lövdal
, Elina van den Brandhof
, Michael Biehl
, Thomas Villmann

Onderzoeksoutput: Conference contribution › Academic › peer review

1 Downloads (Pure)

Samenvatting

We propose a bias detection and mitigating scheme for data in the context of classification tasks based on learning vector quantizers (LVQ) as classifier. For this purpose generalized LVQ endowed with an advanced matrix adaptation scheme is used for bias detection. The bias removal from data is realized applying a nullspace data projection using the adjusted matrix. The usefulness of the approach is demonstrated and illustrated in terms of two real world datasets.

Originele taal-2	English
Titel	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Subtitel	ESANN 2025
Redacteuren	Michel Verleysen
Uitgeverij	Ciaco - i6doc.com
Pagina's	419-424
Aantal pagina's	6
DOI's	https://doi.org/10.14428/esann/2025.ES2025-65
Status	Published - 25-apr.-2025
Evenement	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Brugge, Belgium Duur: 23-apr.-2025 → 25-apr.-2025 Congresnummer: 35 https://www.esann.org

Conference

Conference	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Verkorte titel	ESANN 2025
Land/Regio	Belgium
Stad	Brugge
Periode	23/04/2025 → 25/04/2025
Internet adres	https://www.esann.org

Toegang tot document

10.14428/esann/2025.ES2025-65

Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach – FA(IR)2MA-GLVQFinal publisher's version, 1,68 MBLicentie: Taverne

Handle.net

Permanente koppeling

Citeer dit

Kaden, M., Engelsberger, A., Schubert, R., Lövdal, S., van den Brandhof, E., Biehl, M., & Villmann, T. (2025). Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ. In M. Verleysen (editor), European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2025 (blz. 419-424). Ciaco - i6doc.com. https://doi.org/10.14428/esann/2025.ES2025-65

Kaden, Marika ; Engelsberger, Alexander ; Schubert, Ronny et al. / Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2025. redacteur / Michel Verleysen. Ciaco - i6doc.com, 2025. blz. 419-424

@inproceedings{f18b14da890144058b6422b02dd2b61c,

title = "Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)\textasciicircum{}2MA-GLVQ",

abstract = "We propose a bias detection and mitigating scheme for data in the context of classification tasks based on learning vector quantizers (LVQ) as classifier. For this purpose generalized LVQ endowed with an advanced matrix adaptation scheme is used for bias detection. The bias removal from data is realized applying a nullspace data projection using the adjusted matrix. The usefulness of the approach is demonstrated and illustrated in terms of two real world datasets.",

author = "Marika Kaden and Alexander Engelsberger and Ronny Schubert and Sofie L{\"o}vdal and \{van den Brandhof\}, Elina and Michael Biehl and Thomas Villmann",

year = "2025",

month = apr,

day = "25",

doi = "10.14428/esann/2025.ES2025-65",

language = "English",

pages = "419--424",

editor = "Michel Verleysen",

booktitle = "European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

publisher = "Ciaco - i6doc.com",

note = "European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2025 ; Conference date: 23-04-2025 Through 25-04-2025",

url = "https://www.esann.org",

}

Kaden, M, Engelsberger, A, Schubert, R, Lövdal, S , van den Brandhof, E , Biehl, M & Villmann, T 2025, Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ. in M Verleysen (reds.), European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2025. Ciaco - i6doc.com, blz. 419-424, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Brugge, Belgium, 23/04/2025. https://doi.org/10.14428/esann/2025.ES2025-65

Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ. / Kaden, Marika; Engelsberger, Alexander; Schubert, Ronny et al.
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2025. reds. / Michel Verleysen. Ciaco - i6doc.com, 2025. blz. 419-424.

Onderzoeksoutput: Conference contribution › Academic › peer review

TY - GEN

T1 - Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ

AU - Kaden, Marika

AU - Engelsberger, Alexander

AU - Schubert, Ronny

AU - Lövdal, Sofie

AU - van den Brandhof, Elina

AU - Biehl, Michael

AU - Villmann, Thomas

N1 - Conference code: 35

PY - 2025/4/25

Y1 - 2025/4/25

N2 - We propose a bias detection and mitigating scheme for data in the context of classification tasks based on learning vector quantizers (LVQ) as classifier. For this purpose generalized LVQ endowed with an advanced matrix adaptation scheme is used for bias detection. The bias removal from data is realized applying a nullspace data projection using the adjusted matrix. The usefulness of the approach is demonstrated and illustrated in terms of two real world datasets.

AB - We propose a bias detection and mitigating scheme for data in the context of classification tasks based on learning vector quantizers (LVQ) as classifier. For this purpose generalized LVQ endowed with an advanced matrix adaptation scheme is used for bias detection. The bias removal from data is realized applying a nullspace data projection using the adjusted matrix. The usefulness of the approach is demonstrated and illustrated in terms of two real world datasets.

U2 - 10.14428/esann/2025.ES2025-65

DO - 10.14428/esann/2025.ES2025-65

M3 - Conference contribution

SP - 419

EP - 424

BT - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

A2 - Verleysen, Michel

PB - Ciaco - i6doc.com

T2 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Y2 - 23 April 2025 through 25 April 2025

ER -

Kaden M, Engelsberger A, Schubert R, Lövdal S , van den Brandhof E , Biehl M et al. Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ. In Verleysen M, redacteur, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2025. Ciaco - i6doc.com. 2025. blz. 419-424 doi: 10.14428/esann/2025.ES2025-65

Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)^2MA-GLVQ

Samenvatting

Conference

Toegang tot document

Handle.net

Vingerafdruk

Citeer dit