提出新模型消除时间序列多尺度分析中的冗余特征，提升分类准确率。
DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification
- 通过时序解耦模块分离共享与特定尺度特征
- 引入双重正则化使共享特征一致、特有特征差异显著，最高提升9.71%准确率
- 适合处理复杂时间序列分类任务的研究者或工业应用
真实世界的时间序列通常表现出复杂的时序变化，使得分类任务极具挑战性。近年来的进展表明，多尺度分析方法能有效捕捉这些复杂时序模式。然而，现有基于多尺度分析的时间序列预测方法未能消除跨尺度共享特征的冗余，导致模型对共享特征过度或不足关注。为此，我们提出一种全新的端到端去耦多尺度时间序列分类框架（DisMS-TS）。其核心思想是消除多尺度时间序列中的冗余共享特征，从而提升预测性能。具体而言，我们设计了一个时序解耦模块，分别捕获共享与特定尺度的时序表征；随后，引入两项正则化项，确保所有时间尺度下共享表征的一致性及特有表征的差异性。在多个数据集上的大量实验验证了DisMS-TS优于现有基线方法，准确率最高提升9.71%。
原文摘要 · Abstract (English)
Real-world time series typically exhibit complex temporal variations, making the time series classification task notably challenging. Recent advancements have demonstrated the potential of multi-scale analysis approaches, which provide an effective solution for capturing these complex temporal patterns. However, existing multi-scale analysis-based time series prediction methods fail to eliminate redundant scale-shared features across multi-scale time series, resulting in the model over- or under-focusing on scale-shared features. To address this issue, we propose a novel end-to-end Disentangled Multi-Scale framework for Time Series classification (DisMS-TS). The core idea of DisMS-TS is to eliminate redundant shared features in multi-scale time series, thereby improving prediction performance. Specifically, we propose a temporal disentanglement module to capture scale-shared and scale-specific temporal representations, respectively. Subsequently, to effectively learn both scale-shared and scale-specific temporal representations, we introduce two regularization terms that ensure the consistency of scale-shared representations and the disparity of scale-specific representations across all temporal scales. Extensive experiments conducted on multiple datasets validate the superiority of DisMS-TS over its competitive baselines, with the accuracy improvement up to 9.71%.
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。