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

Qi Huang, Sofoklis Kitharidis, Thomas Bäck, Niki van Stein

2024

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.

Paper Citation

in Harvard Style

Huang Q., Kitharidis S., Bäck T. and van Stein N. (2024). TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification. In Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - Volume 1: EXPLAINS; ISBN 978-989-758-720-7, SciTePress, pages 62-74. DOI: 10.5220/0013066400003886

in Bibtex Style

@conference{explains24,
author={Qi Huang and Sofoklis Kitharidis and Thomas Bäck and Niki van Stein},
title={TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification},
booktitle={Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - Volume 1: EXPLAINS},
year={2024},
pages={62-74},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013066400003886},
isbn={978-989-758-720-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - Volume 1: EXPLAINS
TI - TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification
SN - 978-989-758-720-7
AU - Huang Q.
AU - Kitharidis S.
AU - Bäck T.
AU - van Stein N.
PY - 2024
SP - 62
EP - 74
DO - 10.5220/0013066400003886
PB - SciTePress