U-Cast通过分层结构建模高维时间序列的复杂相关性，提升预测精度与效率。
U-Cast: Learning Hierarchical Structures for High-Dimensional Time Series Forecasting
- 设计分层通道依赖架构，用查询注意力捕捉复杂相关模式
- 在Time-HD数据集上超越基线模型，准确率与效率双提升
- 适用于金融、气象等千通道以上高维时序场景
时间序列预测（TSF）是时间序列分析的核心问题。然而，当时间序列数据集通道数达到数千甚至更多时——我们称之为高维时间序列预测（HDTSF）——带来了传统研究未充分关注的新挑战。HDTSF的难点在于通道间相关性常呈现复杂且分层的结构。现有模型或忽略此类交互，或在维度增长时难以扩展。为此，本文提出U-Cast，一种通道依赖的预测架构，通过创新的查询注意力机制学习潜在的层级通道结构。为解耦高度相关的通道表示，U-Cast在训练中引入全秩正则化。同时，我们发布了Time-HD，首个涵盖大规模、多样化高维数据集的基准。理论证明利用跨通道信息可降低预测风险，实验在Time-HD上显示，U-Cast在准确率和效率上均优于强基线模型。U-Cast与Time-HD共同为未来HDTSF研究奠定坚实基础。
原文摘要 · Abstract (English)
Time series forecasting (TSF) is a central problem in time series analysis. However, as the number of channels in time series datasets scales to the thousands or more, a scenario we define as High-Dimensional Time Series Forecasting (HDTSF), it introduces significant new modeling challenges that are often not the primary focus of traditional TSF research. HDTSF is challenging because the channel correlation often forms complex and hierarchical patterns. Existing TSF models either ignore these interactions or fail to scale as dimensionality grows. To address this issue, we propose U-Cast, a channel-dependent forecasting architecture that learns latent hierarchical channel structures with an innovative query-based attention. To disentangle highly correlated channel representation, U-Cast adds a full-rank regularization during training. We also release Time-HD, the first benchmark of large, diverse, high-dimensional datasets. Our theory shows that exploiting cross-channel information lowers forecasting risk, and experiments on Time-HD demonstrate that U-Cast surpasses strong baselines in both accuracy and efficiency. Together, U-Cast and Time-HD provide a solid basis for future HDTSF research.
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。