检索增强的时间序列预测
Retrieval Augmented Time Series Forecasting
AI总结：
本文提出检索增强预测框架RAF，用于提升时间序列预测的准确性，尤其在大规模模型中效果更显著。
摘要：
检索增强生成（RAG）是现代大语言模型系统的核心组件，特别是在需要最新信息以准确响应用户查询或查询超出训练数据范围的场景中。时间序列基础模型（TSFM）如Chronos的出现以及在各种时间序列领域中有效零样本预测性能的需求，促使我们提出问题：RAG的优势是否同样适用于时间序列预测？本文主张时间序列数据的动态和事件驱动特性使RAG成为TSFM的关键组成部分，并引入一个原则性的RAG框架用于时间序列预测，称为检索增强预测（RAF）。在RAF中，我们开发了高效检索相关时间序列示例并将其纳入预测的策略。通过实验和机制研究，我们证明RAF确实提高了跨多样时间序列领域的预测准确性，且在较大TSFM规模下改进更为显著。
英文摘要：
Retrieval-augmented generation (RAG) is a central component of modern LLM systems, particularly in scenarios where up-to-date information is crucial for accurately responding to user queries or when queries exceed the scope of the training data. The advent of time-series foundation models (TSFM), such as Chronos, and the need for effective zero-shot forecasting performance across various time-series domains motivates the question: Do benefits of RAG similarly carry over to time series forecasting? In this paper, we advocate that the dynamic and event-driven nature of time-series data makes RAG a crucial component of TSFMs and introduce a principled RAG framework for time-series forecasting, called Retrieval Augmented Forecasting (RAF). Within RAF, we develop efficient strategies for retrieving related time-series examples and incorporating them into forecast. Through experiments and mechanistic studies, we demonstrate that RAF indeed improves the forecasting accuracy across diverse time series domains and the improvement is more significant for larger TSFM sizes.
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。
