# Class-Dependent Perturbation Effects in Evaluating Time Series Attributions

arXiv: https://arxiv.org/abs/2502.17022 · HTML: https://mlsanity.com/paper/2502.17022/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [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)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [Towards a Rigorous Evaluation of XAI Methods on Time Series](https://mlsanity.com/paper/1909.07082/) (2019)
- [Evaluation of post-hoc interpretability methods in time-series classification](https://mlsanity.com/paper/2202.05656/) (2022)
- [A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI](https://mlsanity.com/paper/2307.05104/) (2023)
- [Time to Focus: A Comprehensive Benchmark Using Time Series Attribution Methods](https://mlsanity.com/paper/2202.03759/) (2022)
- [Robust Explainer Recommendation for Time Series Classification](https://mlsanity.com/paper/2306.05501/) (2023)
- [Improving the Evaluation and Actionability of Explanation Methods for Multivariate Time Series Classification](https://mlsanity.com/paper/2406.12507/) (2024)
- [Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions](https://mlsanity.com/paper/2310.04178/) (2023)

## Built on by (most cited first, 5 of 5)

- [Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation](https://mlsanity.com/paper/2506.11790/) (2025)
- [xaitimesynth: A Python Package for Evaluating Attribution Methods for Time Series with Synthetic Ground Truth](https://mlsanity.com/paper/2603.06781/) (2026)
- [Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust](https://mlsanity.com/paper/2508.01316/) (2025)
- [Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding](https://mlsanity.com/paper/2603.25251/) (2026)
- [Feature Attribution-Based Explainability Analysis of Deep Learning Models in Predictive Process Monitoring](https://mlsanity.com/paper/2607.17783/) (2026)

## Abstract (arXiv)

As machine learning models become increasingly prevalent in time series applications, Explainable Artificial Intelligence (XAI) methods are essential for understanding their predictions. Within XAI, feature attribution methods aim to identify which input features contribute the most to a model's prediction, with their evaluation typically relying on perturbation-based metrics. Through systematic empirical analysis across multiple datasets, model architectures, and perturbation strategies, we reveal previously overlooked class-dependent effects in these metrics: they show varying effectiveness across classes, achieving strong results for some while remaining less sensitive to others. In particular, we find that the most effective perturbation strategies often demonstrate the most pronounced class differences. Our analysis suggests that these effects arise from the learned biases of classifiers, indicating that perturbation-based evaluation may reflect specific model behaviors rather than intrinsic attribution quality. We propose an evaluation framework with a class-aware penalty term to help assess and account for these effects in evaluating feature attributions, offering particular value for class-imbalanced datasets. Although our analysis focuses on time series classification, these class-dependent effects likely extend to other structured data domains where perturbation-based evaluation is common.