论文标题
出了什么问题，什么时候？实例特征对于时间序列模型的重要性
What went wrong and when? Instance-wise Feature Importance for Time-series Models
论文作者
论文摘要
时间序列模型的解释对于像医疗保健这样的高风险应用程序有用，但在机器学习文献中很少关注。我们提出了FIT，该框架通过量化了随着时间的推移的预测分布的变化来评估观测值对多元时间序列模型的重要性。 FIT基于观测值的重要性，基于其对KL-Divergence下的分布转移的贡献，该贡献将预测分布与未观察到其余特征的反事实形成对比。我们还证明了需要控制时间依赖的分布变化的必要性。我们与模拟和现实世界中的最新基准相比，我们在整个时间序列中识别重要的时间点和观察值方面表明我们的方法优越。
Explanations of time series models are useful for high stakes applications like healthcare but have received little attention in machine learning literature. We propose FIT, a framework that evaluates the importance of observations for a multivariate time-series black-box model by quantifying the shift in the predictive distribution over time. FIT defines the importance of an observation based on its contribution to the distributional shift under a KL-divergence that contrasts the predictive distribution against a counterfactual where the rest of the features are unobserved. We also demonstrate the need to control for time-dependent distribution shifts. We compare with state-of-the-art baselines on simulated and real-world clinical data and demonstrate that our approach is superior in identifying important time points and observations throughout the time series.
