Saved in:
Bibliographic Details
Main Authors: Huang, Qi, Chen, Wei, Bäck, Thomas, van Stein, Niki
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.01343
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.