ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels

By Angus Dempster, Franccois Petitjean, Geoffrey I. Webb. Data mining and knowledge discovery, 2019

1,086 citations recorded by the source corpus.

Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets. Additionally, many existing methods focus on a single type of feature such as shape or frequency. Building on the recent success of convolutional neural networks for time series classification, we show that simple linear classifiers using random convolutional kernels achieve state-of-the-art accuracy with a fraction of the computational expense of existing methods. Using this method, it is possible to train and test a classifier on all 85 ‘bake off’ datasets in the UCR archive in <2h\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<\,2\,\hbox {h}$$\end{document}, and it is possible to train a classifier on a large dataset of more than one million time series in approximately 1 h.

Subfields: Artificial Intelligence, Management Science and Operations Research, Signal Processing

View Paper: https://www.semanticscholar.org/paper/2deafb11372f085d504db87fd626e478d8e965aa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Signal Processing

Citations in the corpus

One Fits All: Power General Time Series Analysis by Pretrained LM (2023, methodology): “XGBoost Chen & Guestrin (2016), Rocket Dempster et al. (2020), LSTNet Lai et al. (2018), LSSL Gu et al. (2021), Pyraformer Liu et al. (2021), TCN Franceschi et al. (2019) and Flowformer Huang et al. (2022) are used for classification.”
MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification (2020, methodology): “For this purpose, following [8], we integrate MiniRocket (and Rocket) with logistic regression, trained using Adam.”
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, background): “However, despite their strong performance, both strategies struggle with scalability for high-dimensional or large datasets [159], [160].”
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency (2022, background): “While representation learning has considerably advanced analysis of time series [7, 8, 9] more broadly [10], learning generalizable representations for temporal data remains a fundamentally challenging problem [8, 11].”