Artificial Intelligence is nowadays ubiquitous, thanks to a continuous process of commodification, revolutionizing but also impacting society at large. In this paper, we address the problem of algorithmic fairness in Machine Learning: ensuring that sensitive information does not unfairly influence the outcome of a classifier. We extend the Fair Empirical Risk Minimization framework (10) where the fair risk minimizer is estimated via constrained empirical risk minimization. In particular, we first propose a new, more general, notion of fairness which translates into a fairness constraint. Then, we propose a new convex relaxation with stronger consistency properties deriving both risk and fairness bounds. By extending our approach to kernel methods, we will also show that the proposal empirically over-performs the state-of-the-art Fair Empirical Risk Minimization approach on several real-world datasets.

Fair Empirical Risk Minimization Revised

Franco D.;Oneto L.;Anguita D.
2023-01-01

Abstract

Artificial Intelligence is nowadays ubiquitous, thanks to a continuous process of commodification, revolutionizing but also impacting society at large. In this paper, we address the problem of algorithmic fairness in Machine Learning: ensuring that sensitive information does not unfairly influence the outcome of a classifier. We extend the Fair Empirical Risk Minimization framework (10) where the fair risk minimizer is estimated via constrained empirical risk minimization. In particular, we first propose a new, more general, notion of fairness which translates into a fairness constraint. Then, we propose a new convex relaxation with stronger consistency properties deriving both risk and fairness bounds. By extending our approach to kernel methods, we will also show that the proposal empirically over-performs the state-of-the-art Fair Empirical Risk Minimization approach on several real-world datasets.
2023
978-3-031-43084-8
978-3-031-43085-5
File in questo prodotto:
File Dimensione Formato  
C123.pdf

accesso chiuso

Tipologia: Documento in Post-print
Dimensione 440.21 kB
Formato Adobe PDF
440.21 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/1163629
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 1
social impact