mlsanityData to 7 Oct 2026

WEASEL 2.0 -- A Random Dilated Dictionary Transform for Fast, Accurate and Memory Constrained Time Series Classification

arXiv 2301.10194 ↗First posted 24 Jan 2023cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

A time series is a sequence of sequentially ordered real values in time. Time series classification (TSC) is the task of assigning a time series to one of a set of predefined classes, usually based on a model learned from examples. Dictionary-based methods for TSC rely on counting the frequency of certain patterns in time series and are important components of the currently most accurate TSC ensembles. One of the early dictionary-based methods was WEASEL, which at its time achieved SotA results while also being very fast. However, it is outperformed both in terms of speed and accuracy by other methods. Furthermore, its design leads to an unpredictably large memory footprint, making it inapplicable for many applications. In this paper, we present WEASEL 2.0, a complete overhaul of WEASEL based on two recent advancements in TSC: Dilation and ensembling of randomized hyper-parameter settings. These two techniques allow WEASEL 2.0 to work with a fixed-size memory footprint while at the same time improving accuracy. Compared to 15 other SotA methods on the UCR benchmark set, WEASEL 2.0 is significantly more accurate than other dictionary methods and not significantly worse than the currently best methods. Actually, it achieves the highest median accuracy over all data sets, and it performs best in 5 out of 12 problem classes. We thus believe that WEASEL 2.0 is a viable alternative for current TSC and also a potentially interesting input for future ensembles.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 24 Jan 2023.

Builds on

18 of 37 references.

References · 18

  1. 2018The UCR Time Series Archivecited by 421
  2. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  3. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  4. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 186
  5. 2020Benchmarking Multivariate Time Series Classification Algorithmscited by 145
  6. 2017LSTM Fully Convolutional Networks for Time Series Classificationcited by 135
  7. 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
  8. 2019catch22: CAnonical Time-series CHaracteristicscited by 103
  9. 2019sktime: A Unified Interface for Machine Learning with Time Seriescited by 98
  10. 2021MultiRocket: Multiple pooling operators and transformations for fast and effective time series classificationcited by 89
  11. 2019TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classificationcited by 67
  12. 2017Multivariate Time Series Classification with WEASEL+MUSEcited by 53
6 more
  1. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 53
  2. 2017Fast and Accurate Time Series Classification with WEASELcited by 47
  3. 2021The Temporal Dictionary Ensemble (TDE) Classifier for Time Series Classificationcited by 26
  4. 2021Random Dilated Shapelet Transform: A New Approach for Time Series Shapeletscited by 22
  5. 2016The Great Time Series Classification Bake Off: An Experimental Evaluation of Recently Proposed Algorithms. Extended Versioncited by 19
  6. 2018From BOP to BOSS and Beyond: Time Series Classification with Dictionary Based Classifierscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 4; 2025: 2; 2026: 4.

15 papers.

Sort:

By area:

  1. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  2. 2024aeon: a Python toolkit for learning from time seriescited by 46
  3. 2023Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fieldscited by 8
  4. 2023Robust Explainer Recommendation for Time Series Classificationcited by 7
  5. 2025MONSTER: Monash Scalable Time Series Evaluation Repositorycited by 6
  6. 2023Finding Foundation Models for Time Series Classification with a PreText Taskcited by 4
  7. 2024Early Classification of Time Series: A Survey and Benchmarkcited by 3
  8. 2023Evaluating Explanation Methods for Multivariate Time Series Classificationcited by 2
  9. 2026In-Context Time Series Classification with Random Convolutional Featurescited by 1
  10. 2024Prevalidated ridge regression is a highly-efficient drop-in replacement for logistic regression for high-dimensional datacited by 0
  11. 2024ECRTime: Ensemble Integration of Classification and Retrieval for Time Series Classificationcited by 0
  12. 2025Learning Interpretable Differentiable Logic Networks for Time-Series Classificationcited by 0
3 more
  1. 2026A Simple State Space Model Excels at Multivariate Time Series Classificationcited by 0
  2. 2026Beyond Simulated Benchmarks: Evaluating Motion Representations for Fall Detection Under Real-World Data Scarcitycited by 0
  3. 2026Revisiting WEASEL 2.0: Reproduction, Sensitivity, and an Adaptive Ensemble-Size Rulecited by 0