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

2024/02/02 by Huang, Qi, Chen, Wei, Bäck, Thomas +1 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2402.01343

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.

Cited by

• Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventions

Related

• Instance-based Counterfactual Explanations for Time Series Classification
• ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
• Interactive Counterfactual Generation for Univariate Time Series
• Shapelet-Based Counterfactual Explanations for Multivariate Time Series
• Implet: A Post-hoc Subsequence Explainer for Time Series Models