MambaSL: Exploring Single-Layer Mamba for Time Series Classification

TL;DR

MambaSL introduces a minimally redesigned single-layer Mamba framework for time series classification, achieving state-of-the-art results and emphasizing reproducibility across diverse datasets.

Contribution

The paper presents MambaSL, a novel single-layer SSM-based framework for TSC, with comprehensive benchmarking and reproducibility enhancements.

Findings

MambaSL achieves statistically significant improvements over baselines.

Re-evaluation across 30 UEA datasets demonstrates robustness.

Public checkpoints enable reproducibility of all evaluated models.

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.