Time Series Model Attribution Visualizations as Explanations
It addresses the problem of explaining deep learning model decisions for time series, which is incremental as it builds on existing attribution methods.
The paper reviews attribution visualization techniques for time series data, highlighting that heatmaps are not always ideal and discussing alternatives, advantages, and disadvantages.
Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.