Self-Interpretable Time Series Prediction with Counterfactual Explanations-猫眼课题宝

DOI：

10.48550/arxiv.2306.06024

发表时间：

2023-06

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Jingquan Yan;Hao Wang

可解释的时间序列预测对于医疗保健和自动驾驶等安全关键领域至关重要。大多数现有的方法侧重于通过为时间序列的片段分配重要分数来解释预测。在本文中，我们采取了一种不同的、更具挑战性的路线，旨在开发一种可自我解释的模型，称为反事实时间序列（Counts），它可以为时间序列预测生成反事实和可操作的解释。具体来说，我们将时间序列反事实解释的问题形式化，建立相关的评估协议，并提出一个变分贝叶斯深度学习模型，该模型具有时间序列溯因、动作和预测的反事实推理能力。与最先进的基线相比，我们的自我解释模型可以产生更好的反事实解释，同时保持相当的预测准确性。

Interpretable time series prediction is crucial for safety-critical areas such as healthcare and autonomous driving. Most existing methods focus on interpreting predictions by assigning important scores to segments of time series. In this paper, we take a different and more challenging route and aim at developing a self-interpretable model, dubbed Counterfactual Time Series (CounTS), which generates counterfactual and actionable explanations for time series predictions. Specifically, we formalize the problem of time series counterfactual explanations, establish associated evaluation protocols, and propose a variational Bayesian deep learning model equipped with counterfactual inference capability of time series abduction, action, and prediction. Compared with state-of-the-art baselines, our self-interpretable model can generate better counterfactual explanations while maintaining comparable prediction accuracy.

Self-Interpretable Time Series Prediction with Counterfactual Explanations

文献摘要

相似文献