OWAdapt: An adaptive loss function for deep learning using OWA operators
Abstract
In this paper, we propose a fuzzy 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, leveraging the power of fuzzy logic 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. Through extensive experimentation, 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 present a default configuration that performs well across different experimental settings.
Cite
@article{arxiv.2305.19443,
title = {OWAdapt: An adaptive loss function for deep learning using OWA operators},
author = {Sebastián Maldonado and Carla Vairetti and Katherine Jara and Miguel Carrasco and Julio López},
journal= {arXiv preprint arXiv:2305.19443},
year = {2023}
}
Comments
15 pages, 1 figure, published