mlsanityData to 7 Oct 2026

TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models

arXiv 2109.08438 ↗First posted 17 Sep 2021cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Time series forecasting is a demanding task ranging from weather to failure forecasting with black-box models achieving state-of-the-art performances. However, understanding and debugging are not guaranteed. We propose TS-MULE, a local surrogate model explanation method specialized for time series extending the LIME approach. Our extended LIME works with various ways to segment and perturb the time series data. In our extension, we present six sampling segmentation approaches for time series to improve the quality of surrogate attributions and demonstrate their performances on three deep learning model architectures and three common multivariate time series datasets.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 10 of its 23 references that are in the map. First posted on arXiv 17 Sep 2021.

Builds on

10 of 23 references.

References · 10

  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. 2018Object Detection with Deep Learning: A Reviewcited by 524
  5. 2019explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learningcited by 69
  6. 2019Towards a Rigorous Evaluation of XAI Methods on Time Seriescited by 67
  7. 2017Clinical Intervention Prediction and Understanding using Deep Networkscited by 35
  8. 2018TSViz: Demystification of Deep Learning Models for Time-Series Analysiscited by 25
  9. 2020timeXplain -- A Framework for Explaining the Predictions of Time Series Classifierscited by 9
  10. 2020An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Taskscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 3; 2024: 9; 2025: 8; 2026: 4.

28 papers.

Sort:

  1. 2024A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecastingcited by 14
  2. 2022Deep Learning Serves Traffic Safety Analysis: A Forward-looking Reviewcited by 13
  3. 2022Motif-guided Time Series Counterfactual Explanationscited by 12
  4. 2023A Deep Dive into Perturbations as Evaluation Technique for Time Series XAIcited by 11
  5. 2023Counterfactual Explanations for Time Series Forecastingcited by 10
  6. 2021Time Series Model Attribution Visualizations as Explanationscited by 8
  7. 2025Which LIME should I trust? Concepts, Challenges, and Solutionscited by 7
  8. 2022Class-Specific Explainability for Deep Time Series Classifierscited by 6
  9. 2024The FIX Benchmark: Extracting Features Interpretable to eXpertscited by 5
  10. 2025Explaining Large Language Models with gSMILEcited by 4
  11. 2024Mapping the Mind of an Instruction-based Image Editing using SMILEcited by 3
  12. 2023Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributionscited by 2
16 more
  1. 2024Developing Guidelines for Functionally-Grounded Evaluation of Explainable Artificial Intelligence using Tabular Datacited by 2
  2. 2025PAX-TS: Model-agnostic multi-granular explanations for time series forecasting via localized perturbationscited by 2
  3. 2024Using a Local Surrogate Model to Interpret Temporal Shifts in Global Annual Datacited by 1
  4. 2024Explaining Clustering of Ecological Momentary Assessment Data Through Temporal and Feature Attentioncited by 1
  5. 2024Explainable Deep Learning Framework for Human Activity Recognitioncited by 1
  6. 2024Surrogate Modeling for Explainable Predictive Time Series Correctionscited by 1
  7. 2025On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Ratingcited by 1
  8. 2024TSFeatLIME: An Online User Study in Enhancing Explainability in Univariate Time Series Forecastingcited by 0
  9. 2025EVolutionary Independent DEtermiNistiC Explanationcited by 0
  10. 2025Evaluating Simplification Algorithms for Interpretability of Time Series Classificationcited by 0
  11. 2025Robust Multi-Modal Forecasting: Integrating Static and Dynamic Featurescited by 0
  12. 2025MUPAX: Multidimensional Problem Agnostic eXplainable AIcited by 0
  13. 2026Interpretability in Deep Time Series Models Demands Semantic Alignmentcited by 0
  14. 2026L2GTX: From Local to Global Time Series Explanationscited by 0
  15. 2026ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AIcited by 0
  16. 2026Feature Attribution-Based Explainability Analysis of Deep Learning Models in Predictive Process Monitoringcited by 0