# FREQuency ATTribution: benchmarking frequency-based occlusion for time series data

arXiv: https://arxiv.org/abs/2506.18481 · HTML: https://mlsanity.com/paper/2506.18481/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [A Survey on the Explainability of Supervised Machine Learning](https://mlsanity.com/paper/2011.07876/) (2020)
- [Measuring the tendency of CNNs to Learn Surface Statistical Regularities](https://mlsanity.com/paper/1711.11561/) (2017)
- [Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain](https://mlsanity.com/paper/2108.08487/) (2021)
- [Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks](https://mlsanity.com/paper/2107.11400/) (2021)
- [Spectral Bias in Practice: The Role of Function Frequency in Generalization](https://mlsanity.com/paper/2110.02424/) (2021)
- [On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions](https://mlsanity.com/paper/1809.04098/) (2018)
- [Towards Frequency-Based Explanation for Robust CNN](https://mlsanity.com/paper/2005.03141/) (2020)
- [A Frequency Perspective of Adversarial Robustness](https://mlsanity.com/paper/2111.00861/) (2021)
- [TSViz: Demystification of Deep Learning Models for Time-Series Analysis](https://mlsanity.com/paper/1802.02952/) (2018)
- [DynaMask: Dynamic Mask Selection for Instance Segmentation](https://mlsanity.com/paper/2303.07868/) (2023)
- [Time Series Model Attribution Visualizations as Explanations](https://mlsanity.com/paper/2109.12935/) (2021)
- [Time to Focus: A Comprehensive Benchmark Using Time Series Attribution Methods](https://mlsanity.com/paper/2202.03759/) (2022)
- [TimeREISE: Time-series Randomized Evolving Input Sample Explanation](https://mlsanity.com/paper/2202.07952/) (2022)
- [Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain](https://mlsanity.com/paper/2305.14979/) (2023)
- [An Attention-based Long Short-Term Memory Framework for Detection of Bitcoin Scams](https://mlsanity.com/paper/2210.14408/) (2022)

## Abstract (arXiv)

Deep neural networks are among the most successful algorithms in terms of performance and scalability across different domains. However, since these networks are black boxes, their usability is severely restricted due to a lack of interpretability. Existing interpretability methods do not address the analysis of time-series-based networks specifically enough. This paper shows that an analysis in the frequency domain can not only highlight relevant areas in the input signal better than existing methods but is also more robust to fluctuations in the signal. In this paper, FreqAtt is presented - a framework that enables post-hoc interpretation of time-series analysis. To achieve this, the relevant frequencies are evaluated, and the signal is either filtered or the relevant input data is marked. FreqAtt is evaluated using a wide range of statistical metrics to provide a broad overview of its performance. The results show that using frequency-based attribution, especially in combination with traditional attribution on top of the frequency-optimized signal, provides strong performance across different metrics.