Skip to content
Niki van Stein
← All publications
PUBLICATION Preprint on arXiv preprint arXiv:2402.01343

Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification

Abstract

In this work, we propose a model-agnostic instance-based post-hoc explainability method for time series classification. The proposed algorithm, namely Time-CF, leverages shapelets and TimeGAN to provide counterfactual explanations for arbitrary time series classifiers. We validate the proposed method on several real-world univariate time series classification tasks from the UCR Time Series Archive. The results indicate that the counterfactual instances generated by Time-CF when compared to state-of-the-art methods, demonstrate better performance in terms of four explainability metrics: closeness, sensibility, plausibility, and sparsity.

Recommended citation

Qi Huang, Wei Chen, Thomas Bäck, Niki van Stein, "Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification." Preprint on arXiv preprint arXiv:2402.01343, 2024.