基础模型与微调：迈向新一代时间序列预测模型
Foundation Models and Fine-Tuning: Toward a New Generation of Models for Time Series Forecasting
浏览论文内容
中文总结 AI 辅助
研究受自然语言处理中大型语言模型突破启发，探讨基础模型用于时间序列预测，回顾其架构、预训练策略等，研究预训练后微调选定基础模型，实证结果表明微调可提高预测精度
中文摘要 AI 辅助
受自然语言处理中大型语言模型近期突破的启发，基础模型已成为零样本时间序列预测的一种有前景的范式，能对预训练期间从未见过的数据集进行准确预测。这些模型参数从数千万到数亿不等，在大量多样的时间序列集合上进行预训练，学习支持点预测和概率预测的可泛化表示。本文回顾了支撑这些模型的主要架构、预训练策略和优化方法，并进一步研究了选定基础模型的预训练后微调以提高其在特定数据集上的性能。实证结果表明，这一步骤始终能提高预测精度。
英文摘要
Inspired by recent breakthroughs in large language models for natural language processing, foundation models have emerged as a promising paradigm for zero-shot time series forecasting, enabling accurate predictions on datasets never seen during pre-training. Ranging from tens to hundreds of millions of parameters, these models are pre-trained on vast and diverse collections of time series, learning generalizable representations that support both point and probabilistic forecasting. This approach alleviates the need for dataset-specific model design and manual tuning, offering a unified solution across forecasting problems. In this work, we review the main architectures, pre-training strategies, and optimization methods underpinning these models. We further investigate post-pre-training fine-tuning of selected foundation models to enhance their performance on specific datasets. Our empirical results demonstrate that this step consistently improves forecasting accuracy over the zero-shot baseline.
发表机构
- Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG（格勒诺布尔阿尔卑斯大学、法国国家科学研究中心、格勒诺布尔国立综合理工学院、信息与地理实验室）
- Savoye（萨瓦亚）
机构由 AI 辅助整理，请以论文原文为准。
