Generalised Triangular Distributions for ordinal deep learning: novel proposal and optimisation
Víctor Manuel Vargas-Yun 
Antonio Manuel Durán-Rosal 
David Guijo-Rubio 
Pedro Antonio Gutiérrez 
César Hervás-Martínez Information Sciences
COMPUTER SCIENCE, INFORMATION SYSTEMS
Abstract
Deep learning techniques for ordinal classification have recently gained significant attention. Predicting an ordinal variable, that is, a variable that demonstrates a natural relationship between categories, is of relevance for a number of real-world problems in various fields of knowledge. For example, a medical diagnosis can occur at different stages of the disease. Applying standard classifiers to ordered labels can lead to errors in distant categories, when errors in an ordinal problem ideally tend to be produced in adjacent classes because of their similarity. To address this issue, we propose a soft labelling approach based on generalised triangular distributions, which are asymmetric and different for each class. The parameters of these distributions are determined using a metaheuristic and are specifically adapted to the given problem. Moreover, this approach enables the model to avoid errors in distant classes (e.g. classifying a patient with a severe disease as healthy). A comprehensive comparison was performed using eight datasets and five performance metrics. The main advantage of the proposed soft-labelling approach is that it adapts the distributions to each problem, resulting in greater flexibility and better performance. The results and statistical analysis show that the proposed methodology significantly outperforms all other methods.
BibTex Citation
@article{Vargas2023Generalised,
author = {Vargas-Yun, V{\' i}ctor Manuel and Dur{\' a}n-Rosal, Antonio Manuel and Guijo-Rubio, David and Guti{\' e}rrez, Pedro Antonio and Herv{\' a}s-Mart{\' i}nez, C{\' e}sar},
journal = {Information Sciences},
doi = {10.1016/j.ins.2023.119606},
year = {2023},
pages = {119606},
title = {Generalised {Triangular} {Distributions} for ordinal deep learning: novel proposal and optimisation},
url = {https://www.sciencedirect.com/science/article/pii/S002002552301191X},
howpublished = {https://www.sciencedirect.com/science/article/pii/S002002552301191X},
volume = {648},
}
BibTex Unicode Citation
@article{Vargas2023Generalised,
author = {Vargas-Yun, Víctor Manuel and Durán-Rosal, Antonio Manuel and Guijo-Rubio, David and Gutiérrez, Pedro Antonio and Hervás-Martínez, César},
journal = {Information Sciences},
doi = {10.1016/j.ins.2023.119606},
year = {2023},
pages = {119606},
title = {Generalised {Triangular} {Distributions} for ordinal deep learning: novel proposal and optimisation},
url = {https://www.sciencedirect.com/science/article/pii/S002002552301191X},
howpublished = {https://www.sciencedirect.com/science/article/pii/S002002552301191X},
volume = {648},
}
APA Citation
Vargas-Yun, V. M., Durán-Rosal, A. M., Guijo-Rubio, D., Gutiérrez, P. A., & Hervás-Martínez, C. (2023). Generalised Triangular Distributions for ordinal deep learning: novel proposal and optimisation. Information Sciences, 648, 119606. https://doi.org/10.1016/j.ins.2023.119606
RIS Citation
TY - JOUR
AU - Vargas-Yun, Víctor Manuel
AU - Durán-Rosal, Antonio Manuel
AU - Guijo-Rubio, David
AU - Gutiérrez, Pedro Antonio
AU - Hervás-Martínez, César
DA - 2023///
PY - 2023
DO - 10.1016/j.ins.2023.119606
ID - temp_id_377693834959
SP - 119606
T2 - Information Sciences
TI - Generalised Triangular Distributions for ordinal deep learning: novel
proposal and optimisation
UR - https://www.sciencedirect.com/science/article/pii/S002002552301191X
VL - 648
ER -
CV Citation
V.M. Vargas-Yun, A.M. Durán-Rosal, D. Guijo-Rubio (CA), P.A. Gutiérrez, C. Hervás-Martínez (1/5). "Generalised Triangular Distributions for ordinal deep learning: novel proposal and optimisation". Information Sciences, Vol. 648, pp. 119606, 2023. (Q1D1, IF: 8.1).