arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.16643cs.AI
收藏

TimeRAG:通过检索增强生成提升 LLM 时间序列预测

TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation

School of Computer Science, Peking University(北京大学计算机学院);College of Computer, National University of Defense Technology(国防科技大学计算机学院)

Silin Yang, Dong Wang, Haoqi Zheng, Ruochun Jin

AI总结:

针对现有基于 LLM 的时间序列预测方法训练成本高且迁移性有限的问题,提出 TimeRAG 框架,通过构建知识库并利用 DTW 检索相似历史序列作为提示,有效提升了预测准确率。

摘要:

尽管大语言模型(LLM)的兴起为时间序列预测引入了新机遇,但现有的基于 LLM 的解决方案需要过多的训练,且迁移性有限。鉴于这些挑战,我们提出了 TimeRAG,一个将检索增强生成(RAG)引入时间序列预测 LLM 的框架。该框架从历史序列构建时间序列知识库,利用动态时间规整(DTW)度量,从知识库中检索与查询序列具有相似模式的参考序列,并将这些参考序列和预测查询结合,作为时间序列预测 LLM 的文本提示。在多个领域数据集上的实验表明,集成 RAG 使原始模型的预测准确率平均提高了 2.97%。

英文摘要:

Although the rise of large language models (LLMs) has introduced new opportunities for time series forecasting, existing LLM-based solutions require excessive training and exhibit limited transferability. In view of these challenges, we propose TimeRAG, a framework that incorporates Retrieval-Augmented Generation (RAG) into time series forecasting LLMs, which constructs a time series knowledge base from historical sequences, retrieves reference sequences from the knowledge base that exhibit similar patterns to the query sequence measured by Dynamic Time Warping (DTW), and combines these reference sequences and the prediction query as a textual prompt to the time series forecasting LLM. Experiments on datasets from various domains show that the integration of RAG improved the prediction accuracy of the original model by 2.97% on average.

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。

↑