TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification

TL;DR

TX-Gen is a multi-objective evolutionary algorithm that generates diverse, sparse, and valid counterfactual explanations for time-series classifiers, enhancing interpretability in critical domains.

Contribution

The paper introduces TX-Gen, a novel multi-objective optimization method using NSGA-II for generating high-quality counterfactual explanations in time-series classification.

Findings

Outperforms existing methods in quality of counterfactuals

Produces diverse and sparse explanations

Improves model interpretability in high-stakes domains

Abstract

In time-series classification, understanding model decisions is crucial for their application in high-stakes domains such as healthcare and finance. Counterfactual explanations, which provide insights by presenting alternative inputs that change model predictions, offer a promising solution. However, existing methods for generating counterfactual explanations for time-series data often struggle with balancing key objectives like proximity, sparsity, and validity. In this paper, we introduce TX-Gen, a novel algorithm for generating counterfactual explanations based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II). TX-Gen leverages evolutionary multi-objective optimization to find a diverse set of counterfactuals that are both sparse and valid, while maintaining minimal dissimilarity to the original time series. By incorporating a flexible reference-guided mechanism, our method improves the plausibility and interpretability of the counterfactuals without relying on predefined assumptions. Extensive experiments on benchmark datasets demonstrate that TX-Gen outperforms existing methods in generating high-quality counterfactuals, making time-series models more transparent and interpretable.