# Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification

arXiv: https://arxiv.org/abs/2408.12666 · HTML: https://mlsanity.com/paper/2408.12666/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 22 Aug 2024.

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

- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [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)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [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)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review](https://mlsanity.com/paper/2010.10596/) (2020)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [Benchmarking Deep Learning Interpretability in Time Series Predictions](https://mlsanity.com/paper/2010.13924/) (2020)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [Instance-based Counterfactual Explanations for Time Series Classification](https://mlsanity.com/paper/2009.13211/) (2020)
- [Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series](https://mlsanity.com/paper/2010.05073/) (2020)
- [Counterfactual Explanations for Machine Learning on Multivariate Time Series Data](https://mlsanity.com/paper/2008.10781/) (2020)
- [Explaining Deep Classification of Time-Series Data with Learned Prototypes](https://mlsanity.com/paper/1904.08935/) (2019)
- [Self-Interpretable Time Series Prediction with Counterfactual Explanations](https://mlsanity.com/paper/2306.06024/) (2023)
- [Motif-guided Time Series Counterfactual Explanations](https://mlsanity.com/paper/2211.04411/) (2022)
- [Multi-Stage Prototype Learning for Interpretable Time Series Classification](https://mlsanity.com/paper/2106.09636/) (2021)
- [Class-Specific Explainability for Deep Time Series Classifiers](https://mlsanity.com/paper/2210.05411/) (2022)

## Built on by (most cited first, 1 of 1)

- [Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventions](https://mlsanity.com/paper/2512.14559/) (2025)

## Abstract (arXiv)

The popularity of deep learning methods in the time series domain boosts interest in interpretability studies, including counterfactual (CF) methods. CF methods identify minimal changes in instances to alter the model predictions. Despite extensive research, no existing work benchmarks CF methods in the time series domain. Additionally, the results reported in the literature are inconclusive due to the limited number of datasets and inadequate metrics. In this work, we redesign quantitative metrics to accurately capture desirable characteristics in CFs. We specifically redesign the metrics for sparsity and plausibility and introduce a new metric for consistency. Combined with validity, generation time, and proximity, we form a comprehensive metric set. We systematically benchmark 6 different CF methods on 20 univariate datasets and 10 multivariate datasets with 3 different classifiers. Results indicate that the performance of CF methods varies across metrics and among different models. Finally, we provide case studies and a guideline for practical usage.