FAIM: Frequency-Aware Interactive Mamba for Time Series Classification

TL;DR

FAIM is a lightweight, frequency-aware model for time series classification that combines adaptive filtering, multi-granularity information interaction, and self-supervised pre-training to improve accuracy, robustness, and efficiency.

Contribution

The paper introduces FAIM, a novel frequency-aware model with adaptive filtering and interactive blocks, enhancing TSC performance over existing methods.

Findings

Outperforms state-of-the-art TSC methods on multiple benchmarks.

Achieves a better balance of accuracy and computational efficiency.

Demonstrates robustness in high-noise and diverse domain scenarios.

Abstract

Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition. TSC tasks require models to effectively capture discriminative information for accurate class identification. Although deep learning architectures excel at capturing temporal dependencies, they often suffer from high computational cost, sensitivity to noise perturbations, and susceptibility to overfitting on small-scale datasets. To address these challenges, we propose FAIM, a lightweight Frequency-Aware Interactive Mamba model. Specifically, we introduce an Adaptive Filtering Block (AFB) that leverages Fourier Transform to extract frequency-domain features from time series data. The AFB incorporates learnable adaptive thresholds to dynamically suppress noise and employs element-wise coupling of global and local semantic adaptive filtering, enabling in-depth modeling of the synergy among different frequency components. Furthermore, we design an Interactive Mamba Block (IMB) to facilitate efficient multi-granularity information interaction, balancing the extraction of fine-grained discriminative features and comprehensive global contextual information, thereby endowing FAIM with powerful and expressive representations for TSC tasks. Additionally, we incorporate a self-supervised pre-training mechanism to enhance FAIM's understanding of complex temporal patterns and improve its robustness across various domains and high-noise scenarios. Extensive experiments on multiple benchmarks demonstrate that FAIM consistently outperforms existing state-of-the-art (SOTA) methods, achieving a superior trade-off between accuracy and efficiency and exhibits outstanding performance.