# Multi-Stage Prototype Learning for Interpretable Time Series Classification

arXiv: https://arxiv.org/abs/2106.09636 · HTML: https://mlsanity.com/paper/2106.09636/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [Interpretable machine learning: definitions, methods, and applications](https://mlsanity.com/paper/1901.04592/) (2019)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Interpretable and Steerable Sequence Learning via Prototypes](https://mlsanity.com/paper/1907.09728/) (2019)
- [Visualizing Deep Networks by Optimizing with Integrated Gradients](https://mlsanity.com/paper/1905.00954/) (2019)
- [Multivariate Time Series Classification with WEASEL+MUSE](https://mlsanity.com/paper/1711.11343/) (2017)
- [Explaining Deep Classification of Time-Series Data with Learned Prototypes](https://mlsanity.com/paper/1904.08935/) (2019)
- [Interpretable Time-series Classification on Few-shot Samples](https://mlsanity.com/paper/2006.02031/) (2020)
- [Scalable Discovery of Time-Series Shapelets](https://mlsanity.com/paper/1503.03238/) (2015)

## Built on by (most cited first, 6 of 6)

- [CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis](https://mlsanity.com/paper/2411.00696/) (2024)
- [Prototype-Based Methods in Explainable AI and Emerging Opportunities in the Geosciences](https://mlsanity.com/paper/2410.19856/) (2024)
- [Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification](https://mlsanity.com/paper/2408.12666/) (2024)
- [Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification](https://mlsanity.com/paper/2603.15939/) (2026)
- [Patronus: Interpretable Diffusion Models with Prototypes](https://mlsanity.com/paper/2503.22782/) (2025)
- [Guided by Stars: Interpretable Concept Learning Over Time Series via Temporal Logic Semantics](https://mlsanity.com/paper/2511.04244/) (2025)

## Abstract (arXiv)

Deep learning methods are powerful tools in classifying multivariate time series data. Despite their high performance, these methods are hard to interpret, which diminishes their applications in high-risk domains such as healthcare. In this paper, we propose a novel multi-stage prototype learning framework for multivariate time series classification. By design, our framework identifies predictive temporal patterns in individual variables as well as cross-variable patterns that are highly predictive of each class. We validate our model on one simulated and four real-world datasets and demonstrate comparable accuracy to state-of-the-art methods while providing substantially improved interpretability through explicit, hierarchical prototype-based explanations. These explanations reveal both single-variable temporal patterns as well as cross-variable interactions that are most predictive for each class, providing insights into underlying mechanisms of the predictive model.