Diffusion Transformers for Tabular Data Time Series Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Garuti, Fabrizio, Sangineto, Enver, Luetto, Simone, Forni, Lorenzo, Cucchiara, Rita
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910913858109440
author Garuti, Fabrizio
Sangineto, Enver
Luetto, Simone
Forni, Lorenzo
Cucchiara, Rita
author_facet Garuti, Fabrizio
Sangineto, Enver
Luetto, Simone
Forni, Lorenzo
Cucchiara, Rita
contents Tabular data generation has recently attracted a growing interest due to its different application scenarios. However, generating time series of tabular data, where each element of the series depends on the others, remains a largely unexplored domain. This gap is probably due to the difficulty of jointly solving different problems, the main of which are the heterogeneity of tabular data (a problem common to non-time-dependent approaches) and the variable length of a time series. In this paper, we propose a Diffusion Transformers (DiTs) based approach for tabular data series generation. Inspired by the recent success of DiTs in image and video generation, we extend this framework to deal with heterogeneous data and variable-length sequences. Using extensive experiments on six datasets, we show that the proposed approach outperforms previous work by a large margin.
format Preprint
id arxiv_https___arxiv_org_abs_2504_07566
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diffusion Transformers for Tabular Data Time Series Generation
Garuti, Fabrizio
Sangineto, Enver
Luetto, Simone
Forni, Lorenzo
Cucchiara, Rita
Machine Learning
Artificial Intelligence
Tabular data generation has recently attracted a growing interest due to its different application scenarios. However, generating time series of tabular data, where each element of the series depends on the others, remains a largely unexplored domain. This gap is probably due to the difficulty of jointly solving different problems, the main of which are the heterogeneity of tabular data (a problem common to non-time-dependent approaches) and the variable length of a time series. In this paper, we propose a Diffusion Transformers (DiTs) based approach for tabular data series generation. Inspired by the recent success of DiTs in image and video generation, we extend this framework to deal with heterogeneous data and variable-length sequences. Using extensive experiments on six datasets, we show that the proposed approach outperforms previous work by a large margin.
title Diffusion Transformers for Tabular Data Time Series Generation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.07566