HIT-ROCKET: Hadamard-vector Inner-product Transformer for ROCKET

TL;DR

HIT-ROCKET introduces a Hadamard-based convolutional transform to enhance the efficiency and accuracy of time series classification, outperforming existing methods while reducing computational costs.

Contribution

The paper presents a novel Hadamard-vector inner-product transformer that improves kernel selection and computational efficiency in ROCKET-based time series classification.

Findings

Achieved at least 5% F1-score improvement over ROCKET.

Reduced training time by 50% compared to miniROCKET.

Enabled deployment on ultra-low-power embedded devices.

Abstract

Time series classification holds broad application value in communications, information countermeasures, finance, and medicine. However, state-of-the-art (SOTA) methods-including HIVE-COTE, Proximity Forest, and TS-CHIEF-exhibit high computational complexity, coupled with lengthy parameter tuning and training cycles. In contrast, lightweight solutions like ROCKET (Random Convolutional Kernel Transform) offer greater efficiency but leave substantial room for improvement in kernel selection and computational overhead. To address these challenges, we propose a feature extraction approach based on Hadamard convolutional transform, utilizing column or row vectors of Hadamard matrices as convolution kernels with extended lengths of varying sizes. This enhancement maintains full compatibility with existing methods (e.g., ROCKET) while leveraging kernel orthogonality to boost computational efficiency, robustness, and adaptability. Comprehensive experiments on multi-domain datasets-focusing on the UCR time series dataset-demonstrate SOTA performance: F1-score improved by at least 5% vs. ROCKET, with 50% shorter training time than miniROCKET (fastest ROCKET variant) under identical hyperparameters, enabling deployment on ultra-low-power embedded devices. All code is available on GitHub.