用多尺度散射变换+注意力机制提升时间序列预测精度
ScatterFusion: A Hierarchical Scattering Transform Framework for Enhanced Time Series Forecasting
- 通过分层散射变换提取跨尺度的时序特征
- 在7个数据集上均优于现有方法，误差显著降低
- 适合需要捕捉长期与短期依赖的时序建模任务
时间序列预测因多时间尺度的复杂时序依赖而面临挑战。本文提出ScatterFusion框架，将散射变换与分层注意力机制协同结合，实现稳健的时间序列预测。该框架包含四个关键组件：(1) 分层散射变换模块（HSTM），提取能捕捉局部与全局模式的多尺度不变特征；(2) 尺度自适应特征增强（SAFE）模块，动态调整不同尺度下的特征重要性；(3) 多分辨率时序注意力（MRTA）机制，学习不同时间跨度的依赖关系；(4) 基于趋势-季节-残差（TSR）分解的结构感知损失函数。在七个基准数据集上的大量实验表明，ScatterFusion在多个预测时长下均显著优于其他主流方法。
原文摘要 · Abstract (English)
Time series forecasting presents significant challenges due to the complex temporal dependencies at multiple time scales. This paper introduces ScatterFusion, a novel framework that synergistically integrates scattering transforms with hierarchical attention mechanisms for robust time series forecasting. Our approach comprises four key components: (1) a Hierarchical Scattering Transform Module (HSTM) that extracts multi-scale invariant features capturing both local and global patterns; (2) a Scale-Adaptive Feature Enhancement (SAFE) module that dynamically adjusts feature importance across different scales; (3) a Multi-Resolution Temporal Attention (MRTA) mechanism that learns dependencies at varying time horizons; and (4) a Trend-Seasonal-Residual (TSR) decomposition-guided structure-aware loss function. Extensive experiments on seven benchmark datasets demonstrate that ScatterFusion outperforms other common methods, achieving significant reductions in error metrics across various prediction horizons.
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。