FreSH: Frequency-Segmented Hierarchical Multi-Expert Framework for Multivariate Time Series Classification
For researchers and practitioners in time series classification, this work offers a more accurate and efficient framework, though the gains are incremental over existing methods.
FreSH, a frequency-segmented hierarchical multi-expert framework, is proposed for multivariate time series classification. It consistently outperforms state-of-the-art methods on 30 UEA benchmark datasets and real-world vibration data, while substantially reducing model size and improving efficiency.
Multivariate Time Series Classification (MTSC) demands models that can effectively capture complex temporal patterns across multiple scales while remaining computationally efficient. However, existing approaches generally struggle to reconcile fine-grained representation learning, especially under class imbalance and real-world constraints. In this paper, we present FreSH, a Frequency-Segmented Hierarchical Multi-Expert Framework designed to address these challenges. FreSH introduces a new perspective for MTSC by enabling adaptive, multi-scale analysis of temporal signals, allowing different aspects of the data to be modeled in a complementary and coordinated manner. By combining localized specialization with holistic context modeling, FreSH achieves strong representational capacity without incurring excessive computational overhead. An adaptive fusion strategy further enhances flexibility, enabling the model to dynamically emphasize the most informative components of the input. In addition, we incorporate a more robust optimization objective that improves learning stability across varying sample difficulties and class distributions. Extensive evaluations on 30 UEA benchmark datasets and real-world vibration data demonstrate that FreSH consistently outperforms state-of-the-art methods in classification accuracy, while substantially reducing model size and efficiency.