Abstract
Time series data are ubiquitous across various domains, making time series analysis critically important. Traditional time series models are task-specific, featuring singular functionality and limited generalization capacity. Recently, large language foundation models have unveiled their remarkable capabilities for cross-task transferability, zero-shot/few-shot learning, and decision-making explainability. This success has sparked interest in the exploration of foundation models to solve multiple time series challenges simultaneously. There are two main research lines, namely \textbf{pre-training foundation models from scratch for time series} and \textbf{adapting large language foundation models for time series}. They both contribute to the development of a unified model that is highly generalizable, versatile, and comprehensible for time series analysis. This survey offers a 3E analytical framework for comprehensive examination of related research. Specifically, we examine existing works from three dimensions, namely \textbf{Effectiveness}, \textbf{Efficiency} and \textbf{Explainability}. In each dimension, we focus on discussing how related works devise tailored solution by considering unique challenges in the realm of time series.Furthermore, we provide a domain taxonomy to help followers keep up with the domain-specific advancements. In addition, we introduce extensive resources to facilitate the field's development, including datasets, open-source, time series libraries. A GitHub repository is also maintained for resource updates (this https URL).
Abstract (translated)
翻译:时间序列数据在各种领域无处不在,使得时间序列分析至关重要。传统的时间序列模型是任务特定的,具有有限的泛化能力。最近,大型语言模型揭示了其在跨任务转移能力、零 shot/少数 shot学习和决策可解释性方面的非凡能力。这一成功引发了人们对基础模型同时解决多个时间序列挑战的探索兴趣。有两个主要的研究方向:从零开始构建时间序列基础模型和调整大型语言模型以应对时间序列。它们都为开发一个高度通用、多才多艺且易于理解的时间序列分析模型做出了贡献。本调查提供了一个3E的分析框架,对相关研究进行全面评估。具体来说,我们从三个维度进行研究,即有效性、效率和可解释性。在每一个维度上,我们关注相关研究如何通过考虑时间序列领域内的独特挑战来制定定制解决方案。此外,我们还为该领域的发展提供了广泛的资源,包括数据集、开源时间和序列库。还维护了一个GitHub仓库,以便于更新资源(此https URL)。
URL
https://arxiv.org/abs/2405.02358