SDGF：融合静态和多尺度动态相关性用于多变量时间序列预测
SDGF: Fusing Static and Multi-Scale Dynamic Correlations for Multivariate Time Series Forecasting
AI总结：
SDGF通过融合静态和多尺度动态相关性，提升多变量时间序列预测的准确性。
摘要：
准确的多变量时间序列预测依赖于系列间的相关性，这些相关性往往在不同的时间尺度上以复杂的方式演变。现有方法在建模这些多尺度依赖关系方面存在局限，并且难以捕捉其复杂和变化的性质。为了解决这一挑战，本文提出了一种新的静态-动态图融合网络（SDGF），其核心在于通过双路径图结构学习方法捕捉多尺度的系列间相关性。具体来说，模型利用基于先验知识的静态图来锚定长期稳定的依赖关系，同时采用多级小波分解提取多尺度特征，以构建一个能够适应性学习的动态图来捕捉不同尺度上的关联。我们设计了一个注意力门控模块，以智能融合这两种互补的信息源，然后使用多核扩张卷积网络来深化对时间模式的理解。在多个广泛使用的现实世界基准数据集上的全面实验表明了我们所提模型的有效性。代码可在https://github.com/shaoxun6033/SDGFNet上获得。
英文摘要：
Accurate multivariate time series forecasting hinges on inter-series correlations, which often evolve in complex ways across different temporal scales. Existing methods are limited in modeling these multi-scale dependencies and struggle to capture their intricate and evolving nature. To address this challenge, this paper proposes a novel Static-Dynamic Graph Fusion network (SDGF), whose core lies in capturing multi-scale inter-series correlations through a dual-path graph structure learning approach. Specifically, the model utilizes a static graph based on prior knowledge to anchor long-term, stable dependencies, while concurrently employing Multi-level Wavelet Decomposition to extract multi-scale features for constructing an adaptively learned dynamic graph to capture associations at different scales. We design an attention-gated module to fuse these two complementary sources of information intelligently, and a multi-kernel dilated convolutional network is then used to deepen the understanding of temporal patterns. Comprehensive experiments on multiple widely used real-world benchmark datasets demonstrate the effectiveness of our proposed model. Code is available at https://github.com/shaoxun6033/SDGFNet.
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。
