发表机构
Baidu, Inc.（百度公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对时间序列预测模型的局限，提出TS-RAG框架，引入参考token融合输入与检索序列信息，在多个真实预测基准上实现最优性能。
AI 中文摘要
尽管深度学习模型，尤其是基于Transformer的架构，在时间序列预测中已展现出出色性能，但检索增强生成（RAG）在该领域的应用仍十分有限。由于RAG已被证实能通过整合相关外部信息提升大语言模型的能力，检索相似时间序列序列作为参考或许也能提高时间序列预测任务的准确性。然而，大多数时间序列模型受限于有限的训练数据、较小的参数规模，以及缺乏大语言模型具备的广泛生成能力。像在语言模型中那样简单地将参考序列拼接进提示词，可能无法得到预期结果。为应对这些挑战，我们提出一种新方法TS-RAG，利用RAG提升预测性能。该框架引入专门设计的参考token，以有效融合输入序列与检索到的相似序列的信息，从而更稳健地捕捉复杂的时间动态。实验结果表明，TS-RAG在多个真实世界预测基准上均达到一致的最先进性能。
英文摘要
While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the application of retrieval-augmented generation (RAG) in this domain remains limited. Since RAG has proven effective in enhancing the capabilities of large language models by incorporating relevant external information, retrieving similar time series sequences as references might also improve accuracy in time series forecasting tasks. However, most time series models are constrained by limited training data, smaller parameter scales, and a lack of the extensive generative capabilities found in large language models. Simply concatenating reference sequences into the prompt, as done in language models, may not yield the expected results. To address these challenges, we propose a novel approach, TS-RAG, which leverages RAG to enhance forecasting performance. The framework introduces specially designed reference tokens to effectively fuse information from the input sequence with that from retrieved similar sequences, enabling a more robust capture of complex temporal dynamics. Experimental results demonstrate that TS-RAG achieves consistent state-of-the-art performance across several real-world forecasting benchmarks.
