TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Daoyu, Cheng, Mingyue, Liu, Zhiding, Liu, Qi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912423232929792
author Wang, Daoyu
Cheng, Mingyue
Liu, Zhiding
Liu, Qi
author_facet Wang, Daoyu
Cheng, Mingyue
Liu, Zhiding
Liu, Qi
contents Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively capture both long-term dynamic evolution and subtle local patterns in a unified manner. In this work, we propose \textbf{TimeDART}, a novel self-supervised time series pre-training framework that unifies two powerful generative paradigms to learn more transferable representations. Specifically, we first employ a causal Transformer encoder, accompanied by a patch-based embedding strategy, to model the evolving trends from left to right. Building on this global modeling, we further introduce a denoising diffusion process to capture fine-grained local patterns through forward diffusion and reverse denoising. Finally, we optimize the model in an autoregressive manner. As a result, TimeDART effectively accounts for both global and local sequence features in a coherent way. We conduct extensive experiments on public datasets for time series forecasting and classification. The experimental results demonstrate that TimeDART consistently outperforms previous compared methods, validating the effectiveness of our approach. Our code is available at https://github.com/Melmaphother/TimeDART.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05711
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
Wang, Daoyu
Cheng, Mingyue
Liu, Zhiding
Liu, Qi
Machine Learning
Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively capture both long-term dynamic evolution and subtle local patterns in a unified manner. In this work, we propose \textbf{TimeDART}, a novel self-supervised time series pre-training framework that unifies two powerful generative paradigms to learn more transferable representations. Specifically, we first employ a causal Transformer encoder, accompanied by a patch-based embedding strategy, to model the evolving trends from left to right. Building on this global modeling, we further introduce a denoising diffusion process to capture fine-grained local patterns through forward diffusion and reverse denoising. Finally, we optimize the model in an autoregressive manner. As a result, TimeDART effectively accounts for both global and local sequence features in a coherent way. We conduct extensive experiments on public datasets for time series forecasting and classification. The experimental results demonstrate that TimeDART consistently outperforms previous compared methods, validating the effectiveness of our approach. Our code is available at https://github.com/Melmaphother/TimeDART.
title TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
topic Machine Learning
url https://arxiv.org/abs/2410.05711