将多变量时间序列预测建模为多任务学习，提升预测精度。
A Multi-Task Learning Approach to Linear Multivariate Forecasting
- 将相似变量聚类分组，构建多任务学习框架
- 按预测误差缩放梯度，实现任务间平衡
- 在多个挑战性数据集上表现优于或持平主流方法
准确预测多变量时间序列在众多工程与科学应用中至关重要。近期先进方法通常忽略变量间的关联，独立处理每个变量，这引发了关于多变量数据建模的若干问题。本文提出将多变量预测视为多任务学习问题，通过分析任务梯度之间的夹角及其平衡性来优化预测。我们以线性模型为基础，通过基于相关性的聚类方式对变量进行分组，从而定义任务；并通过按预测误差缩放梯度实现任务平衡。在此基础上，构建了MTLinear框架，在多个具有挑战性的基准数据集上与强基线对比，结果表明其在多变量预测任务中达到相当或更优的表现。代码已开源：https://github.com/azencot-group/MTLinear。
原文摘要 · Abstract (English)
Accurate forecasting of multivariate time series data is important in many engineering and scientific applications. Recent state-of-the-art works ignore the inter-relations between variates, using their model on each variate independently. This raises several research questions related to proper modeling of multivariate data. In this work, we propose to view multivariate forecasting as a multi-task learning problem, facilitating the analysis of forecasting by considering the angle between task gradients and their balance. To do so, we analyze linear models to characterize the behavior of tasks. Our analysis suggests that tasks can be defined by grouping similar variates together, which we achieve via a simple clustering that depends on correlation-based similarities. Moreover, to balance tasks, we scale gradients with respect to their prediction error. Then, each task is solved with a linear model within our MTLinear framework. We evaluate our approach on challenging benchmarks in comparison to strong baselines, and we show it obtains on-par or better results on multivariate forecasting problems. The implementation is available at: https://github.com/azencot-group/MTLinear
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。