arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04369cs.LG
收藏

多尺度超图与大语言模型:面向时间序列分析的对齐方法

Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis

State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学);College of Computer Science and Technology, Zhejiang University(计算机科学与技术学院,浙江大学)

Zongjiang Shang, Dongliang Cui, Binqing Wu, Ling Chen

AI总结:

本文提出MSH-LLM方法,通过多尺度超图机制和跨模态对齐模块,提升大语言模型在时间序列分析中的表现。

摘要:

最近,利用预训练的大语言模型(LLMs)进行时间序列分析取得了巨大成功。核心思想在于有效对齐自然语言与时间序列之间的模态。然而,自然语言和时间序列的多尺度结构尚未被充分考虑,导致对LLMs能力的利用不足。为此,我们提出MSH-LLM,一种多尺度超图方法,用于时间序列分析中的大语言模型对齐。具体而言,设计了一种超边机制,以增强时间序列语义空间的多尺度语义信息。然后,引入了跨模态对齐(CMA)模块,用于在不同尺度上对自然语言与时间序列之间的模态进行对齐。此外,引入了提示的混合(MoP)机制,以提供上下文信息并增强LLMs理解时间序列多尺度时间模式的能力。在27个真实世界数据集上进行的实验结果表明,MSH-LLM在5种不同应用中均取得了最先进的结果。

英文摘要:

Recently, there has been great success in leveraging pre-trained large language models (LLMs) for time series analysis. The core idea lies in effectively aligning the modality between natural language and time series. However, the multi-scale structures of natural language and time series have not been fully considered, resulting in insufficient utilization of LLMs capabilities. To this end, we propose MSH-LLM, a Multi-Scale Hypergraph method that aligns Large Language Models for time series analysis. Specifically, a hyperedging mechanism is designed to enhance the multi-scale semantic information of time series semantic space. Then, a cross-modality alignment (CMA) module is introduced to align the modality between natural language and time series at different scales. In addition, a mixture of prompts (MoP) mechanism is introduced to provide contextual information and enhance the ability of LLMs to understand the multi-scale temporal patterns of time series. Experimental results on 27 real-world datasets across 5 different applications demonstrate that MSH-LLM achieves the state-of-the-art results.

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。

↑