Multi-SpaCE: Multi-Objective Subsequence-based Sparse Counterfactual Explanations for Multivariate Time Series Classification

TL;DR

Multi-SpaCE is a novel multi-objective genetic algorithm-based method that generates valid, sparse, and contiguous counterfactual explanations for multivariate time series classification, enhancing interpretability.

Contribution

It introduces a multi-objective approach using NSGA-II to produce valid and flexible counterfactuals for multivariate time series, overcoming limitations of prior univariate or rigid methods.

Findings

Achieves perfect validity across diverse datasets.

Outperforms existing methods in sparsity and plausibility.

Provides a Pareto front of solutions for user choice.

Abstract

Deep Learning systems excel in complex tasks but often lack transparency, limiting their use in critical applications. Counterfactual explanations, a core tool within eXplainable Artificial Intelligence (XAI), offer insights into model decisions by identifying minimal changes to an input to alter its predicted outcome. However, existing methods for time series data are limited by univariate assumptions, rigid constraints on modifications, or lack of validity guarantees. This paper introduces Multi-SpaCE, a multi-objective counterfactual explanation method for multivariate time series. Using non-dominated ranking genetic algorithm II (NSGA-II), Multi-SpaCE balances proximity, sparsity, plausibility, and contiguity. Unlike most methods, it ensures perfect validity, supports multivariate data and provides a Pareto front of solutions, enabling flexibility to different end-user needs. Comprehensive experiments in diverse datasets demonstrate the ability of Multi-SpaCE to consistently achieve perfect validity and deliver superior performance compared to existing methods.