paper-with-me

홈 › Papers

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

2025-11-03 · Wang Hao, Kuang Zhang, Hou Chengyu, Yuan Zhonghao, Tan Chenxing, Fu Weifeng, Zhu Yangying arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.01572

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series ClassificationComputational Efficiency

Similar Papers 제목 키워드 기반

Real-Valued Hyperdimensional Sequence Representations with Hadamard Product Binding and Shift Equivariance

2026-08-28 · Kenny Schlegel, Dmitri A. Rachkovskij, Denis Kleyko, Amy Loutfi 외 arxiv

Encoding temporal order is a fundamental requirement for sequence representations in Hyperdimensional Computing. Fractional Power Encoding provides similarity-preserving position vectors whose inner products approximate …

Learning Physical Simulation with Message Passing Transformer

2024-06-10 · Zeyi Xu, Yifei Li

Machine learning methods for physical simulation have achieved significant success in recent years. We propose a new universal architecture based on Graph Neural Network, the Message Passing Transformer, which incorporat…

AttributeDecoderGraph Neural NetworkModel Optimization

Pitch Plane Trajectory Tracking Control for Sounding Rockets via Adaptive Feedback Linearization

2025-01-09 · Pedro dos Santos, Paulo Oliveira

This paper proposes a pitch plane trajectory tacking control solution for suborbital launch vehicles relying on adaptive feedback linearization. Initially, the 2D dynamics and kinematics for a single-engine, thrust-vecto…

Pitch controlPosition

Flashlight: Scalable Link Prediction with Effective Decoders

2022-09-17 · Yiwei Wang, Bryan Hooi, Yozen Liu, Tong Zhao 외

Link prediction (LP) has been recognized as an important task in graph learning with its broad practical applications. A typical application of LP is to retrieve the top scoring neighbors for a given source node, such as…

Graph LearningLink PredictionPrediction

Riemannian Optimization for Hadamard Products of Low-Rank Matrices

2026-05-31 · Pratik Jawanpuria, Ankish Chandresh, Bamdev Mishra arxiv

The elementwise Hadamard product of two low-rank matrices provides a parameter-efficient model for data with multiplicative structure, but its modeling is challenging due to the presence of additional symmetries under co…