Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

0

摘要:
近期,浙江大学和Salesforce的研究人员提出了一种名为VisionTS的时序预测框架,该框架基于何恺明的MAE(Masked Autoencoders)模型,实现了从自然图像中预训练而无需时间序列微调,即可直接在时序预测领域取得显著成效。这一研究揭示了计算机视觉与时间序列预测之间的密切联系,为时序预测领域带来了新的思路。

一、背景
近年来,预训练基础模型在自然语言处理和计算机视觉领域取得了显著成果。然而,将预训练模型应用于时序预测领域仍面临挑战。目前,时序预测主要有两种研究路径:一是将LLM应用于时序预测任务,但语言与时序之间的可迁移性受到质疑;二是直接训练基础模型,但不同领域的时间序列数据之间存在较大差异,限制了迁移效果。

二、研究方法
VisionTS框架基于以下思路:
1. 将时间序列预测任务重构为MAE预训练使用的块级图像补全任务;
2. 将时间序列的历史窗口转换为可见的图像块,预测窗口转换为被遮挡的图像块;
3. 利用MAE模型进行重建与预测。

三、实验结果
VisionTS在涵盖多个领域的35个基准数据集上表现出色,无需时序数据微调的情况下,能够达到最佳预测性能。在零样本情况下,VisionTS甚至超越了Moirai、TimeLLM、GPT4TS等常用时序预测模型。

四、结论
VisionTS框架的提出,为时序预测领域提供了新的思路。这一研究揭示了计算机视觉与时间序列预测之间的密切联系,为未来时序预测技术的发展提供了新的方向。

参考文献:
[1] 陈谋祥, 刘成昊, 等. VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters[C]//arXiv preprint arXiv:2408.17253. https://arxiv.org/abs/2408.17253
[2] 何恺明. Masked Autoencoders Are Unsupervised Learning of Invariant Representations[J]. arXiv preprint arXiv:1912.02751, 2019.


>>> Read more <<<

Views: 0

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注