# Inherently Interpretable Time Series Classification via Multiple Instance Learning

arXiv: https://arxiv.org/abs/2311.10049 · HTML: https://mlsanity.com/paper/2311.10049/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Benchmarking Deep Learning Interpretability in Time Series Predictions](https://mlsanity.com/paper/2010.13924/) (2020)
- [Bake off redux: a review and experimental evaluation of recent time series classification algorithms](https://mlsanity.com/paper/2304.13029/) (2023)
- [TimeSHAP: Explaining Recurrent Models through Sequence Perturbations](https://mlsanity.com/paper/2012.00073/) (2020)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology](https://mlsanity.com/paper/2206.01794/) (2022)
- [HYDRA: Competing convolutional kernels for fast and accurate time series classification](https://mlsanity.com/paper/2203.13652/) (2022)
- [Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency](https://mlsanity.com/paper/2306.02109/) (2023)
- [Temporal Dependencies in Feature Importance for Time Series Predictions](https://mlsanity.com/paper/2107.14317/) (2021)
- [Unsupervised Model Selection for Time-series Anomaly Detection](https://mlsanity.com/paper/2210.01078/) (2022)
- [WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Values](https://mlsanity.com/paper/2211.06507/) (2022)
- [Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning](https://mlsanity.com/paper/2205.15367/) (2022)
- [Model Agnostic Interpretability for Multiple Instance Learning](https://mlsanity.com/paper/2201.11701/) (2022)
- [XAI Methods for Neural Time Series Classification: A Brief Review](https://mlsanity.com/paper/2108.08009/) (2021)
- [Label Propagation for Learning with Label Proportions](https://mlsanity.com/paper/1810.10328/) (2018)
- [Multiple Instance Learning for ECG Risk Stratification](https://mlsanity.com/paper/1812.00475/) (2018)
- [Uncertainty-Aware Multiple Instance Learning from Large-Scale Long Time Series Data](https://mlsanity.com/paper/2111.08625/) (2021)

## Built on by (most cited first, 23 of 23)

- [DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2407.03575/) (2024)
- [TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning](https://mlsanity.com/paper/2405.03140/) (2024)
- [Learning Soft Sparse Shapes for Efficient Time-Series Classification](https://mlsanity.com/paper/2505.06892/) (2025)
- [TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation](https://mlsanity.com/paper/2506.05035/) (2025)
- [From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification](https://mlsanity.com/paper/2408.09449/) (2024)
- [How Effective Can Dropout Be in Multiple Instance Learning ?](https://mlsanity.com/paper/2504.14783/) (2025)
- [Unlocking Pretrained Vision Transformers for Time Series Classification](https://mlsanity.com/paper/2506.08641/) (2025)
- [Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting](https://mlsanity.com/paper/2502.14704/) (2025)
- [Explanation Space: A New Perspective into Time Series Interpretability](https://mlsanity.com/paper/2409.01354/) (2024)
- [Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis](https://mlsanity.com/paper/2507.08178/) (2025)
- [ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models](https://mlsanity.com/paper/2510.20084/) (2025)
- [FIC-TSC: Learning Time Series Classification with Fisher Information Constraint](https://mlsanity.com/paper/2505.06114/) (2025)
- [Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning](https://mlsanity.com/paper/2509.04023/) (2025)
- [Stochastic Sparse Sampling: A Framework for Variable-Length Medical Time Series Classification](https://mlsanity.com/paper/2410.06412/) (2024)
- [Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspection](https://mlsanity.com/paper/2501.16215/) (2025)
- [Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2512.17788/) (2025)
- [On the Necessity of Multi-Domain Explanation: An Uncertainty Principle Approach for Deep Time Series Models](https://mlsanity.com/paper/2506.03267/) (2025)
- [Bridging Neural Networks and Dynamic Time Warping for Adaptive Time Series Classification](https://mlsanity.com/paper/2507.09826/) (2025)
- [TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification](https://mlsanity.com/paper/2601.21289/) (2026)
- [Deep Learning for BioImaging: What Are We Really Learning?](https://mlsanity.com/paper/2603.13377/) (2026)
- [Weakly Supervised Instance-Level Gleason Pattern Estimation Using Primary and Secondary Labels](https://mlsanity.com/paper/2607.23594/) (2026)
- [CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning](https://mlsanity.com/paper/2609.08419/) (2026)
- [Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting](https://mlsanity.com/paper/2609.29317/) (2026)

## 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