mlsanityData to 13 Oct 2026

FreqRISE: Explaining time series using frequency masking

arXiv 2406.13584 ↗First posted 19 Jun 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Time-series data are fundamentally important for many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision making. To develop explainable artificial intelligence in these domains therefore implies explaining salient information in the time series. Current methods for obtaining saliency maps assume localized information in the raw input space. In this paper, we argue that the salient information of a number of time series is more likely to be localized in the frequency domain. We propose FreqRISE, which uses masking-based methods to produce explanations in the frequency and time-frequency domain, and outperforms strong baselines across a number of tasks. The source code is available here: urlhttps://github.com/theabrusch/FreqRISE.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

21 of 31 references.

References · 21

  1. 2017Axiomatic Attribution for Deep Networkscited by 3,368
  2. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,316
  3. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 830
  4. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 258
  5. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 186
  6. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  7. 2020Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAIcited by 125
  8. 2021Explaining Time Series Predictions with Dynamic Maskscited by 73
  9. 2018AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmarkcited by 72
  10. 2021Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Surveycited by 72
  11. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  12. 2021Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directionscited by 42
9 more
  1. 2023The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantuscited by 37
  2. 2023Explainable AI for Time Series via Virtual Inspection Layerscited by 23
  3. 2023Learning Perturbations to Explain Time Series Predictionscited by 23
  4. 2024Explaining Time Series via Contrastive and Locally Sparse Perturbationscited by 22
  5. 2021RELAX: Representation Learning Explainabilitycited by 12
  6. 2023Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approachescited by 9
  7. 2023Multi-view self-supervised learning for multivariate variable-channel time seriescited by 7
  8. 2022TimeREISE: Time-series Randomized Evolving Input Sample Explanationcited by 6
  9. 2021Believe The HiPe: Hierarchical Perturbation for Fast, Robust, and Model-Agnostic Saliency Mappingcited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024FLEXtime: Filterbank learning to explain time seriescited by 6
  2. 2025Time series saliency maps: explaining models across multiple domainscited by 2
  3. 2026Explainable AI Using Inherently Interpretable Components for Wearable-based Health Monitoringcited by 0
  4. 2026Learnable Time-Frequency Masks for Explaining Time-Series Classifierscited by 0