M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps

TL;DR

M-CELS is a novel counterfactual explanation model that improves interpretability of multivariate time series classifiers by generating transparent, valid, and sparse explanations, validated across multiple real-world datasets.

Contribution

Introduces M-CELS, a counterfactual explanation framework guided by learned saliency maps, enhancing interpretability of multivariate time series classification models.

Findings

M-CELS outperforms state-of-the-art baselines in validity, proximity, and sparsity.

Experimental validation on seven real-world datasets shows superior interpretability.

M-CELS provides transparent insights into ML model decisions for multivariate time series.

Abstract

Over the past decade, multivariate time series classification has received great attention. Machine learning (ML) models for multivariate time series classification have made significant strides and achieved impressive success in a wide range of applications and tasks. The challenge of many state-of-the-art ML models is a lack of transparency and interpretability. In this work, we introduce M-CELS, a counterfactual explanation model designed to enhance interpretability in multidimensional time series classification tasks. Our experimental validation involves comparing M-CELS with leading state-of-the-art baselines, utilizing seven real-world time-series datasets from the UEA repository. The results demonstrate the superior performance of M-CELS in terms of validity, proximity, and sparsity, reinforcing its effectiveness in providing transparent insights into the decisions of machine learning models applied to multivariate time series data.