mlsanityData to 7 Oct 2026

MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification

arXiv 2012.08791 ↗First posted 16 Dec 2020cs.LG stat.MLcited by 186

Not on the map. Why?

Abstract (arXiv)

Until recently, the most accurate methods for time series classification were limited by high computational complexity. ROCKET achieves state-of-the-art accuracy with a fraction of the computational expense of most existing methods by transforming input time series using random convolutional kernels, and using the transformed features to train a linear classifier. We reformulate ROCKET into a new method, MINIROCKET, making it up to 75 times faster on larger datasets, and making it almost deterministic (and optionally, with additional computational expense, fully deterministic), while maintaining essentially the same accuracy. Using this method, it is possible to train and test a classifier on all of 109 datasets from the UCR archive to state-of-the-art accuracy in less than 10 minutes. MINIROCKET is significantly faster than any other method of comparable accuracy (including ROCKET), and significantly more accurate than any other method of even roughly-similar computational expense. As such, we suggest that MINIROCKET should now be considered and used as the default variant of ROCKET.

Key facts. Cited by 186 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 19; 2023: 45; 2024: 34; 2025: 30; 2026: 52.

186 papers.

Sort:

By area:

  1. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 165
  2. 2023Bake off redux: a review and experimental evaluation of recent time series classification algorithmscited by 99
  3. 2021MultiRocket: Multiple pooling operators and transformations for fast and effective time series classificationcited by 89
  4. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  5. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 53
  6. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  7. 2023LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Versioncited by 49
  8. 2023Improving Position Encoding of Transformers for Multivariate Time Series Classificationcited by 44
  9. 2022Out-of-Distribution Representation Learning for Time Series Classificationcited by 30
  10. 2023An Approach to Multiple Comparison Benchmark Evaluations that is Stable Under Manipulation of the Comparate Setcited by 27
  11. 2023MBrain: A Multi-channel Self-Supervised Learning Framework for Brain Signalscited by 26
  12. 2024ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysiscited by 26
38 more
  1. 2023BrainNet: Epileptic Wave Detection from SEEG with Hierarchical Graph Diffusion Learningcited by 25
  2. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  3. 2022Dynamic Sparse Network for Time Series Classification: Learning What to "see''cited by 22
  4. 2022Uncertainty-DTW for Time Series and Sequencescited by 21
  5. 2023FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classificationcited by 21
  6. 2023T-Rep: Representation Learning for Time Series using Time-Embeddingscited by 19
  7. 2024Brant-X: A Unified Physiological Signal Alignment Frameworkcited by 16
  8. 2023WEASEL 2.0 -- A Random Dilated Dictionary Transform for Fast, Accurate and Memory Constrained Time Series Classificationcited by 15
  9. 2023QUANT: A Minimalist Interval Method for Time Series Classificationcited by 15
  10. 2021An Efficient Federated Distillation Learning System for Multi-task Time Series Classificationcited by 14
  11. 2024ShapeFormer: Shapelet Transformer for Multivariate Time Series Classificationcited by 14
  12. 2024Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Datacited by 14
  13. 2022HDC-MiniROCKET: Explicit Time Encoding in Time Series Classification with Hyperdimensional Computingcited by 13
  14. 2023Set Features for Fine-grained Anomaly Detectioncited by 13
  15. 2021A Multi-scale Time-series Dataset with Benchmark for Machine Learning in Decarbonized Energy Gridscited by 11
  16. 2023A Multi-Scale Decomposition MLP-Mixer for Time Series Analysiscited by 10
  17. 2024Advancing Time Series Classification with Multimodal Language Modelingcited by 10
  18. 2024TSCMamba: Mamba Meets Multi-View Learning for Time Series Classificationcited by 10
  19. 2022R-GCN: The R Could Stand for Randomcited by 9
  20. 2024Look Into the LITE in Deep Learning for Time Series Classificationcited by 9
  21. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  22. 2022Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifierscited by 8
  23. 2023Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fieldscited by 8
  24. 2024TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Modelscited by 8
  25. 2025Machine-learning for photoplethysmography analysis: Benchmarking feature, image, and signal-based approachescited by 8
  26. 2021MrSQM: Fast Time Series Classification with Symbolic Representationscited by 7
  27. 2022Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Descriptioncited by 7
  28. 2023ShapeWordNet: An Interpretable Shapelet Neural Network for Physiological Signal Classificationcited by 7
  29. 2023Appliance Detection Using Very Low-Frequency Smart Meter Time Seriescited by 7
  30. 2023MTS2Graph: Interpretable Multivariate Time Series Classification with Temporal Evolving Graphscited by 7
  31. 2023Detach-ROCKET: Sequential feature selection for time series classification with random convolutional kernelscited by 7
  32. 2024E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Seriescited by 7
  33. 2024QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Versioncited by 7
  34. 2024Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classificationcited by 7
  35. 2022S-Rocket: Selective Random Convolution Kernels for Time Series Classificationcited by 6
  36. 2023Unleashing the Power of Shared Label Structures for Human Activity Recognitioncited by 6
  37. 2023Time Series Clustering With Random Convolutional Kernelscited by 6
  38. 2024Repurposing Foundation Model for Generalizable Medical Time Series Classificationcited by 6

50 most cited of 186 All 186 (JSON)