Cooperative information systems - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2023

Cooperative information systems

Résumé

Machine Learning is a powerful tool for uncovering relationships and patterns within datasets. However, applying it to a large datasets can lead to biased outcomes and quality issues, due to confounder variables indirectly related to the outcome of interest. Achieving fairness often alters training data, like balancing imbalanced groups (privileged/unprivileged) or excluding sensitive features, impacting accuracy. To address this, we propose a solution inspired by similarity network fusion, preserving dataset structure by integrating global and local similarities. We evaluate our method, considering data set complexity, fairness, and accuracy. Experimental results show the similarity network’s effectiveness in balancing fairness and accuracy. We discuss implications and future directions.

Dates et versions

hal-04257462 , version 1 (25-10-2023)

Identifiants

Citer

Mohamed Sellami, Maria-Esther Vidal, Boudewijn van Dongen, Walid Gaaloul, Hervé Panetto. Cooperative information systems. 14353, Springer Nature Switzerland, pp.505, 2023, Lecture Notes in Computer Science, 978-3-031-46846-9. ⟨10.1007/978-3-031-46846-9⟩. ⟨hal-04257462⟩
66 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More