FreqRISE: Explaining time series using frequency masking

Thea Brüsch, Kristoffer Knutsen Wickstrøm, Mikkel N. Schmidt, Tommy Sonne Alstrøm, Robert Jenssen

Keywords: Explainability, Time series data, Audio data

TL;DR: We present FreqRISE; an explainability method for time series that provides explanations in the frequency and time-frequency domain.

Abstract: Time series data is fundamentally important for many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision-making. To develop explainable artificial intelligence in these domains therefore implies explaining salient information in the time series. Current methods for obtaining saliency maps assumes localized information in the raw input space. In this paper, we argue that the salient information of a number of time series is more likely to be localized in the frequency domain. We propose FreqRISE, which uses masking based methods to produce explanations in the frequency and time-frequency domain, and outperforms strong baselines across a number of tasks.

Git: https://github.com/theabrusch/FreqRISE

Submission Number: 11