MambaSL: Exploring Single-Layer Mamba for Time Series Classification
TLDR
MambaSL, a single-layer Mamba framework, achieves state-of-the-art time series classification performance with a minimal redesign and robust benchmarking.
Key contributions
- Introduces MambaSL, a single-layer Mamba framework for time series classification (TSC).
- Minimally redesigns Mamba's selective SSM and projection layers based on TSC-specific hypotheses.
- Re-evaluates 20 strong baselines across all 30 UEA datasets under a unified, reproducible protocol.
- Achieves state-of-the-art performance in TSC with statistically significant average improvements.
Why it matters
This paper establishes Mamba's potential as a powerful backbone for time series classification, achieving SOTA results. It also provides a much-needed robust and reproducible benchmark for TSC models, addressing previous limitations.
Original Abstract
Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research on their standalone capacity for time series classification (TSC) has remained limited. We propose MambaSL, a framework that minimally redesigns the selective SSM and projection layers of a single-layer Mamba, guided by four TSC-specific hypotheses. To address benchmarking limitations -- restricted configurations, partial University of East Anglia (UEA) dataset coverage, and insufficiently reproducible setups -- we re-evaluate 20 strong baselines across all 30 UEA datasets under a unified protocol. As a result, MambaSL achieves state-of-the-art performance with statistically significant average improvements, while ensuring reproducibility via public checkpoints for all evaluated models. Together with visualizations, these results demonstrate the potential of Mamba-based architectures as a TSC backbone.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.