通过时频协同增强提升多变量时间序列聚类效果
TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
- 引入时频协同增强机制，保留时间依赖与周期性
- 在6个真实数据集上平均提升4.48% NMI指标
- 适合需要高质量时序聚类的工业分析场景
多变量时间序列（MTS）聚类对信号处理与数据分析至关重要。尽管基于对比学习（CL）的深度方法表现突出，但现有模型存在两大缺陷：一是正负样本构建中忽略聚类信息，二是数据增强策略引入不合理归纳偏置，破坏时间依赖与周期性，影响表示质量。本文提出一种时频增强对比学习（TFEC）框架，设计时频协同增强（CoEH）机制，在保持时间结构的同时生成低失真表示；并构建双路径联合优化框架，同步学习表示与聚类分布。在六个真实世界基准数据集上的实验表明，TFEC相比最优方法平均提升4.48% NMI，消融实验证明了各模块有效性。代码已开源。
原文摘要 · Abstract (English)
Multivariate Time-Series (MTS) clustering is crucial for signal processing and data analysis. Although deep learning approaches, particularly those leveraging Contrastive Learning (CL), are prominent for MTS representation, existing CL-based models face two key limitations: 1) neglecting clustering information during positive/negative sample pair construction, and 2) introducing unreasonable inductive biases, e.g., destroying time dependence and periodicity through augmentation strategies, compromising representation quality. This paper, therefore, proposes a Temporal-Frequency Enhanced Contrastive (TFEC) learning framework. To preserve temporal structure while generating low-distortion representations, a temporal-frequency Co-EnHancement (CoEH) mechanism is introduced. Accordingly, a synergistic dual-path representation and cluster distribution learning framework is designed to jointly optimize cluster structure and representation fidelity. Experiments on six real-world benchmark datasets demonstrate TFEC's superiority, achieving 4.48% average NMI gains over SOTA methods, with ablation studies validating the design. The code of the paper is available at: https://github.com/yueliangy/TFEC.
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。