用上下文学习让模型零样本预测时序数据，还能用额外变量提升精度。
Zero-Shot Time Series Forecasting with Covariates via In-Context Learning
- 通过上下文学习融合协变量，实现无需训练的时序预测。
- 在无协变量和有协变量场景下均达到当前最优零样本性能。
- 新数据增强方法解决协变量数据稀缺问题，适合工业级预测应用。
预训练时序模型在零样本预测方面展现出巨大潜力，可提升预测性能并降低使用门槛。然而，现有模型或不支持协变量，或难以有效利用。本文提出COSMIC，一种基于上下文学习的零样本预测模型，能有效利用协变量。为应对协变量数据稀缺问题，我们提出信息性协变量增强方法，使COSMIC可在无协变量数据集的情况下训练。定量与定性分析表明，COSMIC在有无协变量的零样本预测中均表现优异，显著提升了预测能力。
原文摘要 · Abstract (English)
Pretrained time series models, capable of zero-shot forecasting, have demonstrated significant potential in enhancing both the performance and accessibility of time series forecasting. However, existing pretrained models either do not support covariates or fail to incorporate them effectively. We introduce COSMIC, a zero-shot forecasting model that utilizes covariates via in-context learning. To address the challenge of data scarcity, we propose Informative Covariate Augmentation, which enables the training of COSMIC without requiring any datasets that include covariates. COSMIC achieves state-of-the-art performance in zero-shot forecasting, both with and without covariates. Our quantitative and qualitative analysis demonstrates that COSMIC effectively leverages covariates in zero-shot forecasting.
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。