# A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI

arXiv: https://arxiv.org/abs/2307.05104 · HTML: https://mlsanity.com/paper/2307.05104/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 11 Jul 2023.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Towards a Rigorous Evaluation of XAI Methods on Time Series](https://mlsanity.com/paper/1909.07082/) (2019)
- [TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models](https://mlsanity.com/paper/2109.08438/) (2021)
- [An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks](https://mlsanity.com/paper/2012.04344/) (2020)
- [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)

## Built on by (most cited first, 11 of 11)

- [Time is Not Enough: Time-Frequency based Explanation for Time-Series Black-Box Models](https://mlsanity.com/paper/2408.03636/) (2024)
- [Class-Dependent Perturbation Effects in Evaluating Time Series Attributions](https://mlsanity.com/paper/2502.17022/) (2025)
- [Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions](https://mlsanity.com/paper/2310.04178/) (2023)
- [Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation](https://mlsanity.com/paper/2506.11790/) (2025)
- [Explainable time-series forecasting with sampling-free SHAP for Transformers](https://mlsanity.com/paper/2512.20514/) (2025)
- [Explaining Deep Learning-based Anomaly Detection in Energy Consumption Data by Focusing on Contextually Relevant Data](https://mlsanity.com/paper/2501.06099/) (2025)
- [xaitimesynth: A Python Package for Evaluating Attribution Methods for Time Series with Synthetic Ground Truth](https://mlsanity.com/paper/2603.06781/) (2026)
- [Finding the DeepDream for Time Series: Activation Maximization for Univariate Time Series](https://mlsanity.com/paper/2408.10628/) (2024)
- [Adaptive Law-Based Transformation (ALT): A Lightweight Feature Representation for Time Series Classification](https://mlsanity.com/paper/2501.09217/) (2025)
- [Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding](https://mlsanity.com/paper/2603.25251/) (2026)
- [PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention](https://mlsanity.com/paper/2608.07681/) (2026)

## Abstract (arXiv)

Explainable Artificial Intelligence (XAI) has gained significant attention recently as the demand for transparency and interpretability of machine learning models has increased. In particular, XAI for time series data has become increasingly important in finance, healthcare, and climate science. However, evaluating the quality of explanations, such as attributions provided by XAI techniques, remains challenging. This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models. A perturbation analysis involves systematically modifying the input data and evaluating the impact on the attributions generated by the XAI method. We apply this approach to several state-of-the-art XAI techniques and evaluate their performance on three time series classification datasets. Our results demonstrate that the perturbation analysis approach can effectively evaluate the quality of attributions and provide insights into the strengths and limitations of XAI techniques. Such an approach can guide the selection of XAI methods for time series data, e.g., focusing on return time rather than precision, and facilitate the development of more reliable and interpretable machine learning models for time series analysis.