RT info:eu-repo/semantics/article
T1 Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
A1 Villaizán Vallelado, Mario
A1 Salvatori, Matteo
A1 Segura, Carlos
A1 Arapakis, Ioannis
K1 Imputación de datos
K1 Generación de datos sintéticos
K1 Modelo de difusión
K1 Modelo generativo
K1 Transformador
AB Data 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.
PB Association for Computing Machinery
SN 1556-4681
YR 2025
FD 2025
LK https://uvadoc.uva.es/handle/10324/78812
UL https://uvadoc.uva.es/handle/10324/78812
LA eng
NO ACM Transactions on Knowledge Discovery from Data, 2025, vol. 19, n.º 6.
NO Producción Científica
DS UVaDOC
RD 21-oct-2025