TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
This work improves clustering accuracy for multivariate time-series data, which is crucial for signal processing and data analysis, but it is incremental as it builds on existing contrastive learning approaches.
The paper tackled the problem of multivariate time-series clustering by addressing limitations in existing contrastive learning methods, such as neglecting clustering information and introducing unreasonable inductive biases, and proposed a Temporal-Frequency Enhanced Contrastive (TFEC) learning framework, achieving an average 4.48% NMI gain over state-of-the-art methods on six benchmark datasets.
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.