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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Peiyu, Bahri, Omar, Boubrahimi, Soukaina Filali, Hamdi, Shah Muhammad
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909377729921024
author Li, Peiyu
Bahri, Omar
Boubrahimi, Soukaina Filali
Hamdi, Shah Muhammad
author_facet Li, Peiyu
Bahri, Omar
Boubrahimi, Soukaina Filali
Hamdi, Shah Muhammad
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02649
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps
Li, Peiyu
Bahri, Omar
Boubrahimi, Soukaina Filali
Hamdi, Shah Muhammad
Machine Learning
Artificial Intelligence
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.
title M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.02649