为多变量时间序列分类模型提供可解释的反事实解释。
M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps
- 基于学习的显著性图引导生成反事实样本。
- 在7个真实数据集上验证，有效性和稀疏性优于主流方法。
- 适合需要透明决策过程的医疗、金融等场景。
过去十年，多变量时间序列分类受到广泛关注。用于该任务的机器学习模型取得了显著进展，并在众多应用中表现优异。然而，许多先进模型缺乏透明度和可解释性。本文提出M-CELS，一种旨在提升多维时间序列分类可解释性的反事实解释模型。通过在来自UEA数据集仓库的7个真实时间序列数据集上与前沿基线方法对比，实验结果表明，M-CELS在有效性、接近性和稀疏性方面均表现更优，验证了其在揭示机器学习模型决策过程方面的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。