# FreqRISE: Explaining time series using frequency masking

arXiv: https://arxiv.org/abs/2406.13584 · HTML: https://mlsanity.com/paper/2406.13584/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI](https://mlsanity.com/paper/2003.07258/) (2020)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark](https://mlsanity.com/paper/1807.03418/) (2018)
- [Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey](https://mlsanity.com/paper/2104.00950/) (2021)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions](https://mlsanity.com/paper/2111.08446/) (2021)
- [The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus](https://mlsanity.com/paper/2302.07265/) (2023)
- [Explainable AI for Time Series via Virtual Inspection Layers](https://mlsanity.com/paper/2303.06365/) (2023)
- [Learning Perturbations to Explain Time Series Predictions](https://mlsanity.com/paper/2305.18840/) (2023)
- [Explaining Time Series via Contrastive and Locally Sparse Perturbations](https://mlsanity.com/paper/2401.08552/) (2024)
- [RELAX: Representation Learning Explainability](https://mlsanity.com/paper/2112.10161/) (2021)
- [Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches](https://mlsanity.com/paper/2302.01771/) (2023)
- [Multi-view self-supervised learning for multivariate variable-channel time series](https://mlsanity.com/paper/2307.09614/) (2023)
- [TimeREISE: Time-series Randomized Evolving Input Sample Explanation](https://mlsanity.com/paper/2202.07952/) (2022)
- [Believe The HiPe: Hierarchical Perturbation for Fast, Robust, and Model-Agnostic Saliency Mapping](https://mlsanity.com/paper/2103.05108/) (2021)

## Built on by (most cited first, 4 of 4)

- [FLEXtime: Filterbank learning to explain time series](https://mlsanity.com/paper/2411.05841/) (2024)
- [Time series saliency maps: explaining models across multiple domains](https://mlsanity.com/paper/2505.13100/) (2025)
- [Explainable AI Using Inherently Interpretable Components for Wearable-based Health Monitoring](https://mlsanity.com/paper/2603.12880/) (2026)
- [Learnable Time-Frequency Masks for Explaining Time-Series Classifiers](https://mlsanity.com/paper/2609.29270/) (2026)

## 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.