Context Neural Networks：一种可扩展的时间序列预测多变量模型
Context Neural Networks: A Scalable Multivariate Model for Time Series Forecasting
AI总结：
针对现有全局时间序列预测模型未考虑邻接序列状态、多变量模型复杂度高难以扩展的问题，提出线性复杂度的Context Neural Network，通过引入邻接序列实时信息增强预测，兼顾效果与大规模数据的计算可行性。
摘要：
现实世界的时间序列往往呈现出复杂的相互依赖关系，无法孤立地捕捉。全局模型（即对多个相关时间序列的历史数据进行全局建模，同时在局部生成特定序列预测的模型）如今已很常见。然而，它们对每个单独序列的预测仍然是孤立的，未能考虑其相邻序列的当前状态。多变量注意力、图神经网络等多变量模型可以显式整合序列间信息，从而弥补全局模型的不足。但这类技术每个时间步的复杂度为二次型，限制了可扩展性。本文提出Context Neural Network（上下文神经网络），这是一种高效的线性复杂度方法，可为时间序列模型补充来自相邻时间序列的相关上下文洞察，且不会带来显著的计算开销。该方法通过为目标序列提供来自其相邻序列的实时信息来增强预测模型，既解决了全局模型的局限性，又能在大规模数据集上保持计算可行性。
英文摘要：
Real-world time series often exhibit complex interdependencies that cannot be captured in isolation. Global models that model past data from multiple related time series globally while producing series-specific forecasts locally are now common. However, their forecasts for each individual series remain isolated, failing to account for the current state of its neighbouring series. Multivariate models like multivariate attention and graph neural networks can explicitly incorporate inter-series information, thus addressing the shortcomings of global models. However, these techniques exhibit quadratic complexity per timestep, limiting scalability. This paper introduces the Context Neural Network, an efficient linear complexity approach for augmenting time series models with relevant contextual insights from neighbouring time series without significant computational overhead. The proposed method enriches predictive models by providing the target series with real-time information from its neighbours, addressing the limitations of global models, yet remaining computationally tractable for large datasets.
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。
