A Path Towards Fair and Equitable AI Advancing Bias Mitigation in Federated Learning - Archive ouverte HAL Accéder directement au contenu
Poster De Conférence Année : 2023

A Path Towards Fair and Equitable AI Advancing Bias Mitigation in Federated Learning

Résumé

Machine learning has become ubiquitous across various fields as it aids in data analysis and decision-making. The rise of big data has led to the development of decentralized machine learning solutions for increased efficiency. Regulations like GDPR have emerged to safeguard data privacy. In response to security and privacy concerns, Google introduced Federated Learning (FL) in 2016, which holds promise for preserving privacy in ML. However, FL also poses challenges such as addressing bias and ensuring fairness in AI models.
Fichier principal
Vignette du fichier
WISC2023_IEEE_Poster_Ferraguig_Lynda_.pdf (387.67 Ko) Télécharger le fichier
WISC_23_PhD_Forum_Ferraguig_.pdf (712.29 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04158784 , version 1 (11-07-2023)

Identifiants

Citer

Ferraguig Lynda, A Benoit, Faiza Loukil, Mickaël Bettinelli, Christophe Lin-Kwong-Chon. A Path Towards Fair and Equitable AI Advancing Bias Mitigation in Federated Learning. The IEEE International Symposium on Women in Services Computing (WISC 2023), Jul 2023, Chicago, United States. , ⟨10.13140/RG.2.2.23701.29921⟩. ⟨hal-04158784⟩

Collections

UNIV-SAVOIE LISTIC
42 Consultations
38 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More