Motif-guided Time Series Counterfactual Explanations

TL;DR

This paper introduces MG-CF, a novel method that uses motifs to generate interpretable counterfactual explanations for time series models, enhancing trust and transparency in AI decisions.

Contribution

It is the first to leverage motifs for guiding counterfactual explanation generation in time series analysis.

Findings

MG-CF outperforms state-of-the-art baselines in explanation quality.

The method effectively balances interpretability and fidelity.

Validated on five real-world datasets from UCR.

Abstract

With the rising need of interpretable machine learning methods, there is a necessity for a rise in human effort to provide diverse explanations of the influencing factors of the model decisions. To improve the trust and transparency of AI-based systems, the EXplainable Artificial Intelligence (XAI) field has emerged. The XAI paradigm is bifurcated into two main categories: feature attribution and counterfactual explanation methods. While feature attribution methods are based on explaining the reason behind a model decision, counterfactual explanation methods discover the smallest input changes that will result in a different decision. In this paper, we aim at building trust and transparency in time series models by using motifs to generate counterfactual explanations. We propose Motif-Guided Counterfactual Explanation (MG-CF), a novel model that generates intuitive post-hoc counterfactual explanations that make full use of important motifs to provide interpretive information in decision-making processes. To the best of our knowledge, this is the first effort that leverages motifs to guide the counterfactual explanation generation. We validated our model using five real-world time-series datasets from the UCR repository. Our experimental results show the superiority of MG-CF in balancing all the desirable counterfactual explanations properties in comparison with other competing state-of-the-art baselines.