TSCMamba: Mamba Meets Multi-View Learning for Time Series Classification

📅 2024-06-06
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address insufficient modeling of translation equivariance and time-reversal invariance in multivariate time series classification (TSC), this paper proposes a dual-domain (time-frequency) multi-view modeling framework. It integrates frequency-domain spectral features extracted via continuous wavelet transform (CWT) with time-domain representations captured by temporal convolutions or MLPs. Crucially, it introduces the Mamba state-space model—the first such application in TSC—enabling linear-complexity modeling of long sequences. Additionally, a novel “tango” scanning mechanism is designed to enhance joint local-global sequence dependency modeling. Evaluated on ten standard benchmark datasets, the method achieves an average accuracy improvement of 6.45% over state-of-the-art approaches. This work establishes a new paradigm for multivariate TSC that balances theoretical soundness—through principled incorporation of equivariance and invariance properties—with computational efficiency.

Technology Category

Application Category

📝 Abstract
Time series classification (TSC) on multivariate time series is a critical problem. We propose a novel multi-view approach integrating frequency-domain and time-domain features to provide complementary contexts for TSC. Our method fuses continuous wavelet transform spectral features with temporal convolutional or multilayer perceptron features. We leverage the Mamba state space model for efficient and scalable sequence modeling. We also introduce a novel tango scanning scheme to better model sequence relationships. Experiments on 10 standard benchmark datasets demonstrate our approach achieves an average 6.45% accuracy improvement over state-of-the-art TSC models.
Problem

Research questions and friction points this paper is trying to address.

Addresses under-explored properties in time series classification.
Proposes multi-view approach for shift equivariance and inversion invariance.
Enhances accuracy in multivariate time series classification benchmarks.
Innovation

Methods, ideas, or system contributions that make the work stand out.

Multi-view learning captures shift equivariance patterns.
Continuous wavelet transform ensures time-frequency consistency.
Tango scanning enhances Mamba's inversion invariance modeling.
🔎 Similar Papers
No similar papers found.
M
Md. Atik Ahamed
Department of Computer Science, University of Kentucky
Q
Qiang Cheng
Department of Computer Science, Institute for Biomedical Informatics, University of Kentucky