TimePFN：利用合成数据实现高效多元时间序列预测
TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data
AI总结：
TimePFN提出一种基于先验数据拟合网络的新颖训练方案和Transformer架构，利用合成多元时间序列数据，在零样本和少样本预测中超越现有最先进模型，并展现出强大泛化能力。
摘要：
时间序列应用的多样性和特定领域数据的稀缺性凸显了具有强大少样本学习能力的时间序列模型的需求。在这项工作中，我们提出了一种新颖的训练方案和基于Transformer的架构，统称为TimePFN，用于多元时间序列（MTS）预测。TimePFN基于先验数据拟合网络（PFN）的概念，旨在近似贝叶斯推断。我们的方法包括：（1）通过多样化的高斯过程核和线性协同区域化方法生成合成MTS数据，以及（2）一种新颖的MTS架构，能够利用所有输入补丁中的时间依赖和跨通道依赖。我们在多个基准数据集上评估了TimePFN，并证明其在零样本和少样本设置下均优于现有的最先进MTS预测模型。值得注意的是，仅用500个数据点微调TimePFN几乎与全数据集训练误差相当，甚至50个数据点也能产生有竞争力的结果。我们还发现TimePFN表现出强大的单变量预测性能，证明了其泛化能力。总体而言，这项工作释放了合成数据先验在MTS预测中的潜力，并促进了强大的零样本和少样本预测性能。
英文摘要：
The diversity of time series applications and scarcity of domain-specific data highlight the need for time-series models with strong few-shot learning capabilities. In this work, we propose a novel training scheme and a transformer-based architecture, collectively referred to as TimePFN, for multivariate time-series (MTS) forecasting. TimePFN is based on the concept of Prior-data Fitted Networks (PFN), which aims to approximate Bayesian inference. Our approach consists of (1) generating synthetic MTS data through diverse Gaussian process kernels and the linear coregionalization method, and (2) a novel MTS architecture capable of utilizing both temporal and cross-channel dependencies across all input patches. We evaluate TimePFN on several benchmark datasets and demonstrate that it outperforms the existing state-of-the-art models for MTS forecasting in both zero-shot and few-shot settings. Notably, fine-tuning TimePFN with as few as 500 data points nearly matches full dataset training error, and even 50 data points yield competitive results. We also find that TimePFN exhibits strong univariate forecasting performance, attesting to its generalization ability. Overall, this work unlocks the power of synthetic data priors for MTS forecasting and facilitates strong zero- and few-shot forecasting performance.
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。
