Saved in:
Bibliographic Details
Main Authors: Suzuki, Masahiro, Xia, Bohui, Yamamoto, Hiroto, Miyahara, Masanori
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17866
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910231610523648
author Suzuki, Masahiro
Xia, Bohui
Yamamoto, Hiroto
Miyahara, Masanori
author_facet Suzuki, Masahiro
Xia, Bohui
Yamamoto, Hiroto
Miyahara, Masanori
contents Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitation in generating meaningful data. To address this limitation, we propose DAD4TS, a diffusion-model-based data augmentation method with reinforcement learning, designed for time-series forecasting with small-scale data. In DAD4TS, a data generator is simultaneously trained with a time-series model and controlled by a reinforcement learning model to efficiently generate samples that improve the forecast accuracy of the time-series model. To support small-scale data, we use mathematical methods instead of conventional VAE methods to train the diffusion model by projecting the time-series data into the geometric space. We validated the effectiveness of DAD4TS with seven comparative methods through qualitative and quantitative experiments on six real-world datasets and eight time-series models. As a result, DAD4TS was validated on five datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17866
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data
Suzuki, Masahiro
Xia, Bohui
Yamamoto, Hiroto
Miyahara, Masanori
Machine Learning
Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitation in generating meaningful data. To address this limitation, we propose DAD4TS, a diffusion-model-based data augmentation method with reinforcement learning, designed for time-series forecasting with small-scale data. In DAD4TS, a data generator is simultaneously trained with a time-series model and controlled by a reinforcement learning model to efficiently generate samples that improve the forecast accuracy of the time-series model. To support small-scale data, we use mathematical methods instead of conventional VAE methods to train the diffusion model by projecting the time-series data into the geometric space. We validated the effectiveness of DAD4TS with seven comparative methods through qualitative and quantitative experiments on six real-world datasets and eight time-series models. As a result, DAD4TS was validated on five datasets.
title DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data
topic Machine Learning
url https://arxiv.org/abs/2605.17866