FREQuency ATTribution: benchmarking frequency-based occlusion for time series data
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 23 Jun 2025.
Builds on
27 of 42 references.
References · 27
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2018On the Spectral Bias of Neural Networkscited by 1,321
- 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
- 2018Sanity Checks for Saliency Mapscited by 1,149
- 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
- 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
15 more
- 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
- 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
- 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
- 2021Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networkscited by 48
- 2021Spectral Bias in Practice: The Role of Function Frequency in Generalizationcited by 36
- 2018On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functionscited by 31
- 2020Towards Frequency-Based Explanation for Robust CNNcited by 29
- 2021A Frequency Perspective of Adversarial Robustnesscited by 28
- 2018TSViz: Demystification of Deep Learning Models for Time-Series Analysiscited by 25
- 2023DynaMask: Dynamic Mask Selection for Instance Segmentationcited by 10
- 2021Time Series Model Attribution Visualizations as Explanationscited by 8
- 2022Time to Focus: A Comprehensive Benchmark Using Time Series Attribution Methodscited by 8
- 2022TimeREISE: Time-series Randomized Evolving Input Sample Explanationcited by 6
- 2023Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domaincited by 5
- 2022An Attention-based Long Short-Term Memory Framework for Detection of Bitcoin Scamscited by 1
Built on by
Not cited yet.