FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Series
This work addresses the need for efficient and accurate unsupervised clustering of univariate time series, which is important for domains with limited labeled data.
FMMVCC introduces a Mamba-based deep clustering framework for univariate time series that uses state space sequence modeling for efficient temporal representation learning with linear complexity, combined with multi-view self-supervised learning. It outperforms state-of-the-art baselines on 15 benchmark datasets, achieving the best performance in 29 of 60 metric evaluations and the highest average rank.
In many realistic scenarios, large volumes of time series data are generated with limited or expensive annotations. This limitation makes supervised learning methods difficult to apply and leads to the use of unsupervised approaches capable of discovering meaningful structures directly from raw data. Clustering therefore plays a crucial role in organizing time series into groups that share similar temporal patterns, enabling exploratory analysis and downstream tasks without requiring manual labeling. However, existing deep clustering methods often struggle to capture long-range temporal dependencies or rely on architectures with high computational cost. This paper introduces FMMVCC, a Mamba-based deep clustering framework for time series that leverages state space sequence modeling to efficiently learn temporal representations with linear complexity. Additionally, it utilizes multi-view self-supervised learning with temporal masking and augmentations. Experimental evaluation in 15 benchmark datasets proves that FMMVCC consistently outperforms state-of-the-art baselines, achieving the best overall performance in 29 of 60 total metric evaluations and the highest average rank in all tested scenarios.