mlsanityData to 7 Oct 2026

TimeREISE: Time-series Randomized Evolving Input Sample Explanation

arXiv 2202.07952 ↗First posted 16 Feb 2022cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable artificial intelligence addresses this problem. However, most of the interpretability methods are aligned to the image modality by design. The paper introduces TimeREISE a model agnostic attribution method specifically aligned to success in the context of time series classification. The method shows superior performance compared to existing approaches concerning different well-established measurements. TimeREISE is applicable to any time series classification network, its runtime does not scale in a linear manner concerning the input shape and it does not rely on prior data knowledge.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 16 Feb 2022.

Builds on

18 of 35 references.

References · 18

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  4. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  5. 2018Sanity Checks for Saliency Mapscited by 1,149
  6. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  7. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  8. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  9. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  10. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  11. 2018On the Robustness of Interpretability Methodscited by 310
  12. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
6 more
  1. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
  2. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  3. 2021Explaining Time Series Predictions with Dynamic Maskscited by 72
  4. 2018TSViz: Demystification of Deep Learning Models for Time-Series Analysiscited by 25
  5. 2022Time to Focus: A Comprehensive Benchmark Using Time Series Attribution Methodscited by 8
  6. 2020Impact of Legal Requirements on Explainability in Machine Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 1; 2026: 1.

6 papers.

  1. 2024FLEXtime: Filterbank learning to explain time seriescited by 6
  2. 2024FreqRISE: Explaining time series using frequency maskingcited by 4
  3. 2023Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributionscited by 2
  4. 2024Adapting Visualization Techniques for Time-Series Anomaly Detection: From Convolutional Neural Networks to Convolutional-Recurrent Neural Networkscited by 0
  5. 2025FREQuency ATTribution: benchmarking frequency-based occlusion for time series datacited by 0
  6. 2026Learnable Time-Frequency Masks for Explaining Time-Series Classifierscited by 0