Cumulative link models for deep ordinal classification

Authors

Víctor Manuel Vargas-Yun

Pedro Antonio Gutiérrez

César Hervás-Martínez

Published in Journal

Neurocomputing

COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE.

Impact Factor JCR 2020

5.719

JCR Ranking

30 / 140

Position

ISSN 0925-2312

Vol. 401

Pages 48-58

Abstract

This paper proposes a deep convolutional neural network model for ordinal regression by considering a family of probabilistic ordinal link functions in the output layer. The link functions are those used for cumulative link models, which are traditional statistical linear models based on projecting each pattern into a 1-dimensional space. A set of ordered thresholds splits this space into the different classes of the problem. In our case, the projections are estimated by a non-linear deep neural network. To further improve the results, we combine these ordinal models with a loss function that takes into account the distance between the categories, based on the weighted Kappa index. Three different link functions are studied in the experimental study, and the results are contrasted with statistical analysis. The experiments run over two different ordinal classification problems and the statistical tests confirm that these models improve the results of a nominal model and outperform other robust proposals considered in the literature.

Keywords

cumulative link models deep learning kappa index ordinal regression

BibTex Citation

@article{Vargas2020Cumulative,
	author = {Vargas-Yun, V{\' i}ctor Manuel and Guti{\' e}rrez, Pedro Antonio and Herv{\' a}s-Mart{\' i}nez, C{\' e}sar},
	journal = {Neurocomputing},
	doi = {10.1016/j.neucom.2020.03.034},
	year = {2020},
	pages = {48--58},
	title = {Cumulative link models for deep ordinal classification},
	url = {https://doi.org/10.1016/j.neucom.2020.03.034},
	howpublished = {https://doi.org/10.1016/j.neucom.2020.03.034},
	volume = {401},
}

BibTex Unicode Citation

@article{Vargas2020Cumulative,
	author = {Vargas-Yun, Víctor Manuel and Gutiérrez, Pedro Antonio and Hervás-Martínez, César},
	journal = {Neurocomputing},
	doi = {10.1016/j.neucom.2020.03.034},
	year = {2020},
	pages = {48--58},
	title = {Cumulative link models for deep ordinal classification},
	url = {https://doi.org/10.1016/j.neucom.2020.03.034},
	howpublished = {https://doi.org/10.1016/j.neucom.2020.03.034},
	volume = {401},
}

APA Citation

Vargas-Yun, V. M., Gutiérrez, P. A., & Hervás-Martínez, C. (2020). Cumulative link models for deep ordinal classification. Neurocomputing, 401, 48–58. https://doi.org/10.1016/j.neucom.2020.03.034

RIS Citation

TY  - JOUR
AU  - Vargas-Yun, Víctor Manuel
AU  - Gutiérrez, Pedro Antonio
AU  - Hervás-Martínez, César
DA  - 2020///
PY  - 2020
DO  - 10.1016/j.neucom.2020.03.034
ID  - temp_id_783059085965
SP  - 48-58
T2  - Neurocomputing
TI  - Cumulative link models for deep ordinal classification
UR  - https://doi.org/10.1016/j.neucom.2020.03.034
VL  - 401
ER  -

CV Citation

V.M. Vargas-Yun (CA), P.A. Gutiérrez, C. Hervás-Martínez (1/3). "Cumulative link models for deep ordinal classification". Neurocomputing,  Vol. 401, pp. 48-58, 2020. (Q1, IF: 5.7).