用自适应小波引导注意力，提升多尺度时间序列预测精度
AWGformer: Adaptive Wavelet-Guided Transformer for Multi-Resolution Time Series Forecasting
- 通过动态选择小波基和分解层级，捕捉信号特征
- 跨尺度融合机制让不同频段特征交互更有效
- 适合处理非平稳、多尺度的复杂时间序列数据
时间序列预测需同时捕捉多时序模式并保持计算效率。本文提出AWGformer，通过自适应小波分解与跨尺度注意力机制，增强多变量时间序列预测能力。其核心包括：(1) 自适应小波分解模块（AWDM），根据信号特征动态选择最优小波基和分解层级；(2) 跨尺度特征融合机制（CSFF），利用可学习耦合矩阵捕获不同频段间交互；(3) 频率感知多头注意力（FAMA），按注意力头的频率选择性加权；(4) 分层预测网络（HPN），在多分辨率下生成预测后重构。在基准数据集上的实验表明，AWGformer显著优于当前最优方法，尤其在多尺度和非平稳时间序列上表现突出。理论分析提供了收敛性保证，并建立波浪引导注意力与经典信号处理原理的联系。
原文摘要 · Abstract (English)
Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel architecture that integrates adaptive wavelet decomposition with cross-scale attention mechanisms for enhanced multi-variate time series prediction. Our approach comprises: (1) an Adaptive Wavelet Decomposition Module (AWDM) that dynamically selects optimal wavelet bases and decomposition levels based on signal characteristics; (2) a Cross-Scale Feature Fusion (CSFF) mechanism that captures interactions between different frequency bands through learnable coupling matrices; (3) a Frequency-Aware Multi-Head Attention (FAMA) module that weights attention heads according to their frequency selectivity; (4) a Hierarchical Prediction Network (HPN) that generates forecasts at multiple resolutions before reconstruction. Extensive experiments on benchmark datasets demonstrate that AWGformer achieves significant average improvements over state-of-the-art methods, with particular effectiveness on multi-scale and non-stationary time series. Theoretical analysis provides convergence guarantees and establishes the connection between our wavelet-guided attention and classical signal processing principles.
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。