用检索增强提升时间序列预测精度，尤其对大模型效果更显著
Retrieval Augmented Time Series Forecasting
- 从历史数据中检索相似时间序列，辅助当前预测
- 在多个数据集上提升预测准确率，大模型提升更明显
- 适合需要零样本预测的跨领域时间序列任务
检索增强生成（RAG）是现代大语言模型的关键组件，尤其在需实时信息或超出训练数据范围的场景中。随着时间序列基础模型（TSFM），如Chronos的出现，以及跨领域零样本预测的需求，我们提出：RAG的益处是否同样适用于时间序列预测？本文主张，时间序列的动态与事件驱动特性使其成为构建有效预测模型的关键。为此，我们提出一种系统性RAG框架——检索增强预测（RAF），设计高效检索相关时序样本并融入预测的方法。实验与机制分析表明，RAF在多种时间序列领域均提升预测精度，且对更大规模的TSFM提升更显著。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。