arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.09656cs.LGcs.CL
收藏

LLM-PS:利用时间模式与语义赋能大语言模型进行时间序列预测

LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics

Nanjing University of Science and Technology(南京理工大学);Nanjing University(南京大学);Shanghai Jiao Tong University(上海交通大学);Wuhan University(武汉大学);Nanyang Technological University(南洋理工大学)

Jialiang Tang, Shuo Chen, Chen Gong, Jing Zhang, Dacheng Tao

AI总结:

针对现有LLM时间序列预测忽视数据内在特性的问题,提出LLM-PS框架,通过多尺度卷积网络捕捉时间模式并结合时间到文本模块提取连续时间语义,在短期、长期及少样本、零样本预测中均取得最优性能。

摘要:

时间序列预测(TSF)在金融规划和健康监测等许多现实领域至关重要。近期研究表明,大语言模型(LLMs)凭借其强大的上下文建模能力,在TSF方面具有巨大潜力。然而,现有基于LLM的方法通常表现不佳,因为它们忽视了时间序列数据的内在特性。与LLM预训练中使用的文本数据不同,时间序列数据语义稀疏,且包含独特的时间模式。为解决这一问题,我们提出LLM-PS,通过学习时间序列数据中的基本模式和有意义的语义来赋能LLM进行TSF。我们的LLM-PS引入了一种新的多尺度卷积神经网络,擅长捕捉时间序列中的短期波动和长期趋势。同时,我们引入了一个时间到文本模块,用于在连续时间区间内提取有价值的语义,而非孤立的时间点。通过整合这些模式和语义,LLM-PS有效建模时间依赖关系,实现对时间序列的深度理解并提供准确预测。大量实验结果表明,LLM-PS在短期和长期预测任务以及少样本和零样本设置下均达到了最先进的性能。

英文摘要:

Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Recent studies have revealed that Large Language Models (LLMs), with their powerful in-contextual modeling capabilities, hold significant potential for TSF. However, existing LLM-based methods usually perform suboptimally because they neglect the inherent characteristics of time series data. Unlike the textual data used in LLM pre-training, the time series data is semantically sparse and comprises distinctive temporal patterns. To address this problem, we propose LLM-PS to empower the LLM for TSF by learning the fundamental \textit{Patterns} and meaningful \textit{Semantics} from time series data. Our LLM-PS incorporates a new multi-scale convolutional neural network adept at capturing both short-term fluctuations and long-term trends within the time series. Meanwhile, we introduce a time-to-text module for extracting valuable semantics across continuous time intervals rather than isolated time points. By integrating these patterns and semantics, LLM-PS effectively models temporal dependencies, enabling a deep comprehension of time series and delivering accurate forecasts. Intensive experimental results demonstrate that LLM-PS achieves state-of-the-art performance in both short- and long-term forecasting tasks, as well as in few- and zero-shot settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑