Diffusion Models for Tabular Data Imputation and Synthetic Data Generation

Producción Científica

Detalles Bibliográficos
Autores: Villaizán Vallelado, Mario, Salvatori, Matteo, Segura, Carlos, Arapakis, Ioannis
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Universidad de Valladolid
Repositorio:UVaDOC. Repositorio Documental de la Universidad de Valladolid
OAI Identifier:oai:uvadoc.uva.es:10324/78812
Acceso en línea:https://doi.org/10.1145/3742435
https://uvadoc.uva.es/handle/10324/78812
Access Level:acceso abierto
Palabra clave:Imputación de datos
Generación de datos sintéticos
Modelo de difusión
Modelo generativo
Transformador
1209.03 Análisis de Datos
id ES_0c079780ecadae33639cdf3168c1962d
oai_identifier_str oai:uvadoc.uva.es:10324/78812
network_acronym_str ES
network_name_str España
repository_id_str
spelling Diffusion Models for Tabular Data Imputation and Synthetic Data GenerationVillaizán Vallelado, MarioSalvatori, MatteoSegura, CarlosArapakis, IoannisImputación de datosGeneración de datos sintéticosModelo de difusiónModelo generativoTransformador1209.03 Análisis de DatosProducción CientíficaData imputation and data generation have important applications across many domains where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful generative models capable of capturing complex data distributions across various data modalities such as image, audio, and time series. Recently, they have been also adapted to generate tabular data. In this article, we propose a diffusion model for tabular data that introduces three key enhancements: (1) a conditioning attention mechanism, (2) an encoder-decoder transformer as the denoising network, and (3) dynamic masking. The conditioning attention mechanism is designed to improve the model’s ability to capture the relationship between the condition and synthetic data. The transformer layers help model interactions within the condition (encoder) or synthetic data (decoder), while dynamic masking enables our model to efficiently handle both missing data imputation and synthetic data generation tasks within a unified framework. We conduct a comprehensive evaluation by comparing the performance of diffusion models with transformer conditioning against state-of-the-art techniques such as Variational Autoencoders, Generative Adversarial Networks, and Diffusion Models, on benchmark datasets. Our evaluation focuses on the assessment of the generated samples with respect to three important criteria, namely: (1) machine learning efficiency, (2) statistical similarity, and (3) privacy risk mitigation. For the task of data imputation, we consider the efficiency of the generated samples across different levels of missing features. The results demonstrate average superior machine learning efficiency and statistical accuracy compared to the baselines, while maintaining privacy risks at a comparable level, particularly showing increased performance in datasets with a large number of features. By conditioning the data generation on a desired target variable, the model can mitigate systemic biases, generate augmented datasets to address data imbalance issues, and improve data quality for subsequent analysis. This has significant implications for domains such as healthcare and finance, where accurate, unbiased, and privacy-preserving data are critical for informed decision-making and fair model outcomes.Unión Europea-Horizonte 2020: 101168560Association for Computing Machinery2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://doi.org/10.1145/3742435https://uvadoc.uva.es/handle/10324/78812reponame:UVaDOC. Repositorio Documental de la Universidad de Valladolidinstname:Universidad de ValladolidIngléshttps://dl.acm.org/doi/pdf/10.1145/3742435info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-nd/4.0/oai:uvadoc.uva.es:10324/788122026-06-13T12:44:47Z
dc.title.none.fl_str_mv Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
title Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
spellingShingle Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
Villaizán Vallelado, Mario
Imputación de datos
Generación de datos sintéticos
Modelo de difusión
Modelo generativo
Transformador
1209.03 Análisis de Datos
title_short Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
title_full Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
title_fullStr Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
title_full_unstemmed Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
title_sort Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
dc.creator.none.fl_str_mv Villaizán Vallelado, Mario
Salvatori, Matteo
Segura, Carlos
Arapakis, Ioannis
author Villaizán Vallelado, Mario
author_facet Villaizán Vallelado, Mario
Salvatori, Matteo
Segura, Carlos
Arapakis, Ioannis
author_role author
author2 Salvatori, Matteo
Segura, Carlos
Arapakis, Ioannis
author2_role author
author
author
dc.subject.none.fl_str_mv Imputación de datos
Generación de datos sintéticos
Modelo de difusión
Modelo generativo
Transformador
1209.03 Análisis de Datos
topic Imputación de datos
Generación de datos sintéticos
Modelo de difusión
Modelo generativo
Transformador
1209.03 Análisis de Datos
description Producción Científica
publishDate 2025
dc.date.none.fl_str_mv 2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://doi.org/10.1145/3742435
https://uvadoc.uva.es/handle/10324/78812
url https://doi.org/10.1145/3742435
https://uvadoc.uva.es/handle/10324/78812
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv https://dl.acm.org/doi/pdf/10.1145/3742435
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Association for Computing Machinery
publisher.none.fl_str_mv Association for Computing Machinery
dc.source.none.fl_str_mv reponame:UVaDOC. Repositorio Documental de la Universidad de Valladolid
instname:Universidad de Valladolid
instname_str Universidad de Valladolid
reponame_str UVaDOC. Repositorio Documental de la Universidad de Valladolid
collection UVaDOC. Repositorio Documental de la Universidad de Valladolid
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403261425942528
score 15,811543

Similares en LA Referencia