With the rise in the employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual modalities, time-series data has been neglected with only a handful of methods tested due to their poor intelligibility. We approach the problem of interpretability in a novel way by proposing TSInsight where we attach an auto-encoder to the classifier with a sparsity-inducing norm on its output and fine-tune it based on the gradients from the classifier and a reconstruction penalty. TSInsight learns to preserve features that are important for prediction by the classifier and suppresses those that are irrelevant i.e. serves as a feature attribution method to boost interpretability. In contrast to most other attribution frameworks, TSInsight is capable of generating both instance-based and model-based explanations. We evaluated TSInsight along with 9 other commonly used attribution methods on 8 different time-series datasets to validate its efficacy. Evaluation results show that TSInsight naturally achieves output space contraction, therefore, is an effective tool for the interpretability of deep time-series models.

中文翻译：

---

TSInsight：用于时间序列数据可解释性的本地-全局归因框架

随着深度学习方法在安全关键场景中使用的增加，可解释性比以往任何时候都更加重要。尽管已经为视觉模式探索了许多关于可解释性的不同方向，但时间序列数据由于可理解性差而被忽略，只有少数方法进行了测试。我们通过提出 TSInsight 以一种新颖的方式解决可解释性问题，在该方法中，我们将自动编码器附加到分类器，在其输出上使用稀疏诱导范数，并根据分类器的梯度和重建惩罚对其进行微调。TSInsight 学会保留对分类器预测很重要的特征，并抑制那些不相关的特征，即作为一种特征归因方法来提高可解释性。与大多数其他归因框架相比，TSInsight 能够生成基于实例和基于模型的解释。我们在 8 个不同的时间序列数据集上评估了 TSInsight 以及 9 种其他常用的归因方法，以验证其有效性。评估结果表明，TSInsight 自然地实现了输出空间收缩，因此是深度时间序列模型可解释性的有效工具。