mlsanityData to 7 Oct 2026

ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts

arXiv 2511.02152 ↗First posted 4 Nov 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Time series data is one of the most popular data modalities in critical domains such as industry and medicine. The demand for algorithms that not only exhibit high accuracy but also offer interpretability is crucial in such fields, as decisions made there bear significant consequences. In this paper, we present ProtoTSNet, a novel approach to interpretable classification of multivariate time series data, through substantial enhancements to the ProtoPNet architecture. Our method is tailored to overcome the unique challenges of time series analysis, including capturing dynamic patterns and handling varying feature significance. Central to our innovation is a modified convolutional encoder utilizing group convolutions, pre-trainable as part of an autoencoder and designed to preserve and quantify feature importance. We evaluated our model on 30 multivariate time series datasets from the UEA archive, comparing our approach with existing explainable methods as well as non-explainable baselines. Through comprehensive evaluation and ablation studies, we demonstrate that our approach achieves the best performance among ante-hoc explainable methods while maintaining competitive performance with non-explainable and post-hoc explainable approaches, providing interpretable results accessible to domain experts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 44 references that are in the map. First posted on arXiv 4 Nov 2025.

Builds on

21 of 44 references.

References · 21

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  5. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  6. 2018The UEA multivariate time series classification archive, 2018cited by 330
  7. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 270
  8. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  9. 2023Bake off redux: a review and experimental evaluation of recent time series classification algorithmscited by 99
  10. 2019sktime: A Unified Interface for Machine Learning with Time Seriescited by 98
  11. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  12. 2019Interpretable and Steerable Sequence Learning via Prototypescited by 72
9 more
  1. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 64
  2. 2020Interpretable Time Series Classification using Linear Models and Multi-resolution Multi-domain Symbolic Representationscited by 31
  3. 2019Explaining Deep Classification of Time-Series Data with Learned Prototypescited by 30
  4. 2023An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learningcited by 25
  5. 2020XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classificationcited by 24
  6. 2023Natural Example-Based Explainability: a Surveycited by 13
  7. 2020Interpretable Time-series Classification on Few-shot Samplescited by 11
  8. 2022dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classificationcited by 11
  9. 2024Look Into the LITE in Deep Learning for Time Series Classificationcited by 9

Built on by

Not cited yet.