OWAdapt: an adaptive loss function for deep learning using OWA operators

Simple item page
dc.coverageDOI: 10.1016/j.knosys.2023.111022
dc.creatorMaldonado, Sebastián
dc.creatorVairetti, Carla
dc.creatorJara, Katherine
dc.creatorCarrasco, Miguel
dc.creatorLópez, Julio
dc.date2023
dc.date.accessioned2026-01-05T21:05:42Z
dc.date.available2026-01-05T21:05:42Z
dc.description<p>In this paper, we propose a novel adaptive loss function for enhancing deep learning performance in classification tasks. Specifically, we redefine the cross-entropy loss to effectively address class-level noise conditions, including the challenging problem of class imbalance. Our approach introduces aggregation operators to improve classification accuracy. The rationale behind our proposed method lies in the iterative up-weighting of class-level components within the loss function, focusing on those with larger errors. To achieve this, we employ the ordered weighted average (OWA) operator and combine it with an adaptive scheme for gradient-based learning. The main finding is that our method outperforms other commonly used loss functions, such as the standard cross-entropy or focal loss, across various binary and multiclass classification tasks. Furthermore, we explore the influence of hyperparameters associated with the OWA operators and propose a default configuration that performs well across different experimental settings.</p>eng
dc.identifierhttps://investigadores.uandes.cl/en/publications/da75e4fb-5d2c-4075-8103-059b6ae473c6
dc.identifier.urihttps://repositorio.uandes.cl/handle/uandes/62075
dc.languageeng
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.sourcevol.280 (2023) date: 2023-11-25 p.1-9
dc.subjectClass-imbalance classification
dc.subjectDeep learning
dc.subjectLoss functions
dc.subjectOWA operators
dc.titleOWAdapt: an adaptive loss function for deep learning using OWA operatorseng
dc.typeArticleeng
dc.typeArtículospa
Files
Collections
Pure-CRIS