mlsanityData to 7 Oct 2026

Inherently Interpretable Time Series Classification via Multiple Instance Learning

arXiv 2311.10049 ↗First posted 16 Nov 2023cs.LG cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

Conventional Time Series Classification (TSC) methods are often black boxes that obscure inherent interpretation of their decision-making processes. In this work, we leverage Multiple Instance Learning (MIL) to overcome this issue, and propose a new framework called MILLET: Multiple Instance Learning for Locally Explainable Time series classification. We apply MILLET to existing deep learning TSC models and show how they become inherently interpretable without compromising (and in some cases, even improving) predictive performance. We evaluate MILLET on 85 UCR TSC datasets and also present a novel synthetic dataset that is specially designed to facilitate interpretability evaluation. On these datasets, we show MILLET produces sparse explanations quickly that are of higher quality than other well-known interpretability methods. To the best of our knowledge, our work with MILLET, which is available on GitHub (https://github.com/JAEarly/MILTimeSeriesClassification), is the first to develop general MIL methods for TSC and apply them to an extensive variety of domains

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

30 of 45 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  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. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  7. 2018Deep learning for time series classification: a reviewcited by 575
  8. 2018The UCR Time Series Archivecited by 421
  9. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  10. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
  11. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  12. 2016Revisiting Multiple Instance Neural Networkscited by 119
18 more
  1. 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
  2. 2020Benchmarking Deep Learning Interpretability in Time Series Predictionscited by 102
  3. 2023Bake off redux: a review and experimental evaluation of recent time series classification algorithmscited by 99
  4. 2020TimeSHAP: Explaining Recurrent Models through Sequence Perturbationscited by 73
  5. 2021Explaining Time Series Predictions with Dynamic Maskscited by 72
  6. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  7. 2022Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathologycited by 58
  8. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 53
  9. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  10. 2021Temporal Dependencies in Feature Importance for Time Series Predictionscited by 27
  11. 2022Unsupervised Model Selection for Time-series Anomaly Detectioncited by 24
  12. 2022WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Valuescited by 24
  13. 2022Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learningcited by 13
  14. 2022Model Agnostic Interpretability for Multiple Instance Learningcited by 10
  15. 2021XAI Methods for Neural Time Series Classification: A Brief Reviewcited by 7
  16. 2018Label Propagation for Learning with Label Proportionscited by 5
  17. 2018Multiple Instance Learning for ECG Risk Stratificationcited by 5
  18. 2021Uncertainty-Aware Multiple Instance Learning from Large-Scale Long Time Series Datacited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 13; 2026: 5.

23 papers.

Sort:

  1. 2024DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classificationcited by 25
  2. 2024TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learningcited by 12
  3. 2025Learning Soft Sparse Shapes for Efficient Time-Series Classificationcited by 10
  4. 2025TIMING: Temporality-Aware Integrated Gradients for Time Series Explanationcited by 9
  5. 2024From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classificationcited by 7
  6. 2025How Effective Can Dropout Be in Multiple Instance Learning ?cited by 7
  7. 2025Unlocking Pretrained Vision Transformers for Time Series Classificationcited by 6
  8. 2025Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecastingcited by 4
  9. 2024Explanation Space: A New Perspective into Time Series Interpretabilitycited by 3
  10. 2025Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysiscited by 3
  11. 2025ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Modelscited by 3
  12. 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraintcited by 2
11 more
  1. 2025Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learningcited by 2
  2. 2024Stochastic Sparse Sampling: A Framework for Variable-Length Medical Time Series Classificationcited by 1
  3. 2025Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspectioncited by 1
  4. 2025On the Necessity of Multi-Domain Explanation: An Uncertainty Principle Approach for Deep Time Series Modelscited by 0
  5. 2025Bridging Neural Networks and Dynamic Time Warping for Adaptive Time Series Classificationcited by 0
  6. 2025Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learningcited by 0
  7. 2026TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classificationcited by 0
  8. 2026Deep Learning for BioImaging: What Are We Really Learning?cited by 0
  9. 2026Weakly Supervised Instance-Level Gleason Pattern Estimation Using Primary and Secondary Labelscited by 0
  10. 2026CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learningcited by 0
  11. 2026Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecastingcited by 0