TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning

TL;DR

This paper introduces TFEC, a novel contrastive learning framework for multivariate time-series clustering that preserves temporal and frequency information, leading to improved clustering accuracy on benchmark datasets.

Contribution

The paper proposes a Temporal-Frequency Enhanced Contrastive learning framework with a CoEH mechanism and dual-path representation for better MTS clustering.

Findings

Achieves 4.48% higher NMI than state-of-the-art methods.

Validates effectiveness through extensive experiments on six datasets.

Ablation studies confirm the importance of each component.

Abstract

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.