发表机构
Beihang University（北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出m-WCN框架，通过神经化GHM多小波分解联合提取时间与频率特征，并构建TFBC和FTB分别用于分类与预测，在64个UCR数据集和七个基准上平均提升19.97%和19.92%。
AI 中文摘要
时间序列分析在金融、医疗和气象等领域中至关重要。现实世界中的时间序列通常表现出由多种潜在因素塑造的多尺度特征，导致复杂的时间模式和丰富的频率结构。然而，现有方法通常仅关注频域分解或时域模式提取，忽视了两者的联合结构。这种解耦建模限制了表示的表达能力，并削弱了需要同时进行时间和频谱推理的任务的性能。为弥补这一空白，我们提出了m-WCN，一种新颖的端到端深度学习框架，通过神经化多小波分解来联合提取时间模式和频率成分。通过使用可训练的卷积算子近似经典GHM多小波变换并施加正交性约束，m-WCN生成可解释的多分辨率表示。在此基础上，我们引入了两种任务特定架构：用于时间序列分类的TFBC，增强跨频率尺度的判别特征；以及用于预测的FTB，集成频率感知预测器。在64个UCR数据集和七个公开预测基准上的大量实验证明了我们方法的有效性。基于神经化的m-WCN，我们的TFBC和FTB在多种数据集上优于各种基线模型，在分类任务中平均提升19.97%，在预测任务中平均提升19.92%。
英文摘要
Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by diverse latent factors, resulting in intricate temporal patterns and rich frequency structures. However, existing approaches typically focus on either frequency-domain decomposition or time-domain pattern extraction in isolation, neglecting their joint structure. This decoupled modeling limits representation expressiveness and undermines performance in tasks requiring simultaneous temporal and spectral reasoning. To address this gap, we propose m-WCN, a novel end-to-end deep learning framework that neuralizes multi-wavelet decomposition for joint extraction of temporal patterns and frequency components. By approximating the classical GHM multi-wavelet transform with trainable convolutional operators and enforcing orthogonality constraints, m-WCN produces interpretable multi-resolution representations. Built on this foundation, we introduce two task-specific architectures: TFBC for time series classification, which boosts discriminative features across frequency scales, and FTB for forecasting, which ensembles frequency-aware predictors. Extensive experiments on 64 UCR datasets and seven public forecasting benchmarks demonstrate the effectiveness of our approach. Built on the neuralized m-WCN, our TFBC and FTB outperform various baseline models across diverse datasets, achieving average improvements of 19.97% in classification and 19.92% in forecasting tasks.
Comments17 pages, 3 figures
