Time Series Model Attribution Visualizations as Explanations

Udo Schlegel, Daniel Keim

External link (DOI)
View presentation:2021-10-24T15:40:00ZGMT-0600Change your timezone on the schedule page
2021-10-24T15:40:00Z
Exemplar figure, but none was provided by the authors
Fast forward

Direct link to video on YouTube: https://youtu.be/yK0zCVIVoWY

Abstract

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 survey, 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.