A self-regulated convolutional neural network for classifying variable stars

Simple item page
dc.article.numberstaf840
dc.catalogadorgjm
dc.contributor.authorPérez Galarce, Francisco Javier
dc.contributor.authorMartínez-Palomera, J.
dc.contributor.authorPichara Baksai, Karim Elías
dc.contributor.authorHuijse, P.
dc.contributor.authorCatelan, Márcio
dc.date.accessioned2025-05-28T14:34:45Z
dc.date.available2025-05-28T14:34:45Z
dc.date.issued2025
dc.description.abstractOver the last two decades, machine learning models have been widely applied and have proven effective in classifying variable stars, particularly with the adoption of deep learning architectures such as convolutional neural networks, recurrent neural networks, and transformer models. While these models have achieved high accuracy, they require high-quality, representative data and a large number of labelled samples for each star type to generalise well, which can be challenging in time-domain surveys. This challenge often leads to models learning and reinforcing biases inherent in the training data, an issue that is not easily detectable when validation is performed on subsamples from the same catalogue. The problem of biases in variable star data has been largely overlooked, and a definitive solution has yet to be established. In this paper, we propose a new approach to improve the reliability of classifiers in variable star classification by introducing a self-regulated training process. This process utilises synthetic samples generated by a physics-enhanced latent space variational autoencoder, incorporating six physical parameters from Gaia Data Release 3. Our method features a dynamic interaction between a classifier and a generative model, where the generative model produces ad-hoc synthetic light curves to reduce confusion during classifier training and populate underrepresented regions in the physical parameter space. Experiments conducted under various scenarios demonstrate that our self-regulated training approach outperforms traditional training methods for classifying variable stars on biased datasets, showing statistically significant improvements.
dc.fechaingreso.objetodigital2025-05-28
dc.format.extent21 páginas
dc.fuente.origenORCID
dc.identifier.doi10.1093/mnras/staf840
dc.identifier.urihttps://doi.org/10.1093/mnras/staf840
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/104494
dc.information.autorucEscuela de Ingeniería; Pérez Galarce, Francisco Javier; 0000-0002-6921-298X; 1050243
dc.information.autorucEscuela de Ingeniería; Pichara Baksai, Karim Elías; 0000-0002-9372-5574; 6541
dc.information.autorucInstituto de Astrofísica; Catelan, Márcio; 0000-0001-6003-8877; 1001556
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaMonthly Notices of the Royal Astronomical Society
dc.rightsacceso abierto
dc.rights.licenseCC BY 4.0 Attribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectstars: variables
dc.subjectmethods: data analysis
dc.subjectmethods: analytical
dc.subjectmethods: statistical
dc.subjectastronomical data bases: miscellaneous
dc.subject.ddc520
dc.subject.deweyAstronomíaes_ES
dc.titleA self-regulated convolutional neural network for classifying variable stars
dc.typeartículo
sipa.codpersvinculados1050243
sipa.codpersvinculados6541
sipa.codpersvinculados1001556
sipa.trazabilidadORCID;2025-05-26
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
staf840.pdf
Size:
2.25 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas