Diffusion Models for Tabular Data Imputation and Synthetic Data Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Villaizán-Vallelado, Mario, Salvatori, Matteo, Segura, Carlos, Arapakis, Ioannis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915332224974848
author Villaizán-Vallelado, Mario
Salvatori, Matteo
Segura, Carlos
Arapakis, Ioannis
author_facet Villaizán-Vallelado, Mario
Salvatori, Matteo
Segura, Carlos
Arapakis, Ioannis
contents Data imputation and data generation have important applications for many domains, like healthcare and finance, 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 data. Recently, they have been also adapted to generate tabular data. In this paper, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
Villaizán-Vallelado, Mario
Salvatori, Matteo
Segura, Carlos
Arapakis, Ioannis
Machine Learning
Data imputation and data generation have important applications for many domains, like healthcare and finance, 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 data. Recently, they have been also adapted to generate tabular data. In this paper, 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.
title Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
topic Machine Learning
url https://arxiv.org/abs/2407.02549