AdaPTS：将单变量基础模型适配于概率性多变量时间序列预测

摘要

预训练基础模型（FMs）在单变量时间序列预测任务中展现了卓越的性能。然而，仍存在若干实际挑战，包括处理特征间复杂的依赖关系以及量化预测中的不确定性。本研究旨在通过引入适配器来解决这些关键限制；适配器作为特征空间转换工具，能够有效利用预训练的单变量时间序列FMs处理多变量任务。适配器的工作原理是将多变量输入投影至合适的潜在空间，并独立地对每个维度应用FM。受表示学习和部分随机贝叶斯神经网络文献的启发，我们提出了一系列适配器及优化/推理策略。在合成和真实世界数据集上的实验验证了适配器的有效性，相较于基线方法，在预测精度和不确定性量化方面均实现了显著提升。我们的框架AdaPTS将适配器定位为一种模块化、可扩展且高效的解决方案，用于在多变量场景中利用时间序列FMs，从而推动其在现实世界应用中的广泛采用。代码已发布于https://github.com/abenechehab/AdaPTS。

English

Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managing intricate dependencies among features and quantifying uncertainty in predictions. This study aims to tackle these critical limitations by introducing adapters; feature-space transformations that facilitate the effective use of pre-trained univariate time series FMs for multivariate tasks. Adapters operate by projecting multivariate inputs into a suitable latent space and applying the FM independently to each dimension. Inspired by the literature on representation learning and partially stochastic Bayesian neural networks, we present a range of adapters and optimization/inference strategies. Experiments conducted on both synthetic and real-world datasets confirm the efficacy of adapters, demonstrating substantial enhancements in forecasting accuracy and uncertainty quantification compared to baseline methods. Our framework, AdaPTS, positions adapters as a modular, scalable, and effective solution for leveraging time series FMs in multivariate contexts, thereby promoting their wider adoption in real-world applications. We release the code at https://github.com/abenechehab/AdaPTS.

AdaPTS：将单变量基础模型适配于概率性多变量时间序列预测

AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting

摘要

Summary

Support