基于Shapelet的时间序列分类模型无关反事实局部解释
Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification
AI总结：
本研究提出面向时间序列分类的模型无关事后可解释算法Time-CF，结合shapelets与TimeGAN生成反事实解释，在UCR数据集多任务上四项可解释性指标均优于现有最优方法。
摘要：
本研究提出了一种面向时间序列分类的、模型无关的基于实例的事后可解释性方法。所提出的算法名为Time-CF，利用shapelets（形状子）和TimeGAN为任意时间序列分类器提供反事实解释。我们在UCR时间序列档案库的多个真实世界单变量时间序列分类任务上验证了该方法。结果表明，与当前最优方法相比，Time-CF生成的反事实实例在接近性、敏感性、合理性、稀疏性四项可解释性指标上表现更优。
英文摘要：
In this work, we propose a model-agnostic instance-based post-hoc explainability method for time series classification. The proposed algorithm, namely Time-CF, leverages shapelets and TimeGAN to provide counterfactual explanations for arbitrary time series classifiers. We validate the proposed method on several real-world univariate time series classification tasks from the UCR Time Series Archive. The results indicate that the counterfactual instances generated by Time-CF when compared to state-of-the-art methods, demonstrate better performance in terms of four explainability metrics: closeness, sensibility, plausibility, and sparsity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
