Sub-SpaCE: Subsequence-Based Sparse Counterfactual Explanations for Time Series Classification Problems

The interpretation of existing machine learning models has become a critical task to facilitate the widespread adoption of AI across different domains, leading to the emergent field of eXplainable AI (XAI). However, dedicated approaches for time series data have received limited attention compared to XAI methods for images or tabular data. Moreover, current approaches often overlook the unique challenges present in time series classification problems. In this paper, we introduce Subsequence-based Sparse Counterfactual Explanations (Sub-SpaCE), a novel method tailored for time series classification problems. Sub-SpaCE employs genetic algorithms, with customized mutation and initialization processes, promoting changes in a small number of subsequences to generate highly sparse and plausible counterfactual explanations. Our empirical evaluations on various datasets demonstrate Sub-SpaCE’s excellent performance, achieving a good balance between sparsity and plausibility in counterfactual explanations for time series data.