Extracting Interpretable Local and Global Representations from Attention on Time Series

This paper targets two transformer attention based interpretability methods working with local abstraction and global representation, in the context of time series data. We distinguish local and global contexts, and provide a comprehensive framework for both general interpretation options. We discuss their specific instantiation via different methods in detail, also outlining their respective computational implementation and abstraction variants. Furthermore, we provide extensive experimentation demonstrating the efficacy of the presented approaches. In particular, we perform our experiments using a selection of univariate datasets from the UCR UEA time series repository where we both assess the performance of the proposed approaches, as well as their impact on explainability and interpretability/complexity. Here, with an extensive analysis of hyperparameters, the presented approaches demonstrate an significant improvement in interpretability/complexity, while capturing many core decisions of and maintaining a similar performance to the baseline model. Finally, we draw general conclusions outlining and guiding the application of the presented methods.