论文标题
评估多元时间序列预测的本地解释方法
Evaluation of Local Explanation Methods for Multivariate Time Series Forecasting
论文作者
论文摘要
能够解释机器学习模型是机器学习的许多应用中的关键任务。具体而言，局部解释性对于确定模型为什么做出特定预测很重要。尽管最近关注AI的可解释性，但对于时间序列预测的局部解释性方法缺乏研究，而少数主要集中在时间序列分类任务上的可解释方法。在这项研究中，我们提出了两个新的评估指标，以预测时间序列：回归和消融百分比阈值的扰动曲线面积。这两个指标可以衡量局部解释模型的当地保真度。我们扩展了理论基础，以在两个流行的数据集\ textit {rossmann销售}和\ textit {electricity}上收集实验结果。这两个指标都可以对众多本地解释模型进行全面比较，并发现哪些指标更敏感。最后，我们为此分析提供了启发性的推理。
Being able to interpret a machine learning model is a crucial task in many applications of machine learning. Specifically, local interpretability is important in determining why a model makes particular predictions. Despite the recent focus on AI interpretability, there has been a lack of research in local interpretability methods for time series forecasting while the few interpretable methods that exist mainly focus on time series classification tasks. In this study, we propose two novel evaluation metrics for time series forecasting: Area Over the Perturbation Curve for Regression and Ablation Percentage Threshold. These two metrics can measure the local fidelity of local explanation models. We extend the theoretical foundation to collect experimental results on two popular datasets, \textit{Rossmann sales} and \textit{electricity}. Both metrics enable a comprehensive comparison of numerous local explanation models and find which metrics are more sensitive. Lastly, we provide heuristical reasoning for this analysis.
