MSHyper：用于长程时间序列预测的多尺度超图Transformer
MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting
AI总结：
针对长程时间序列预测中高阶交互建模能力不足的问题，提出多尺度超图Transformer框架MSHyper，通过引入多尺度超图、超边图和三阶段消息传递机制来建模高阶模式交互，在五个真实数据集上取得SOTA性能。
摘要：
揭示不同尺度时间模式之间的相互作用是实现精确长程时间序列预测的基础。然而，以往的研究缺乏对高阶交互进行建模的能力。为了促进长程时间序列预测中更全面的模式交互建模，我们提出了一种多尺度超图Transformer（MSHyper）框架。具体而言，引入多尺度超图以为高阶模式交互建模提供基础。随后，通过将超边视为节点，我们还构建了超边图以增强超图建模。此外，引入了三阶段消息传递机制，以聚合模式信息并学习不同尺度时间模式之间的交互强度。在五个真实世界数据集上的大量实验表明，MSHyper在各种设置下均实现了最先进的（SOTA）性能。
英文摘要：
Demystifying interactions between temporal patterns of different scales is fundamental to precise long-range time series forecasting. However, previous works lack the ability to model high-order interactions. To promote more comprehensive pattern interaction modeling for long-range time series forecasting, we propose a Multi-Scale Hypergraph Transformer (MSHyper) framework. Specifically, a multi-scale hypergraph is introduced to provide foundations for modeling high-order pattern interactions. Then by treating hyperedges as nodes, we also build a hyperedge graph to enhance hypergraph modeling. In addition, a tri-stage message passing mechanism is introduced to aggregate pattern information and learn the interaction strength between temporal patterns of different scales. Extensive experiments on five real-world datasets demonstrate that MSHyper achieves state-of-the-art (SOTA) performance across various settings.
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。
