FreqRISE: Explaining time series using frequency masking

Thea Brüsch, Kristoffer Knutsen Wickstrøm, Mikkel N. Schmidt, Tommy Sonne Alstrøm, Robert Jenssen
6/19/2024
cs.LG

Official code: theabrusch/FreqRISE (3 stars, last commit 2024-12-13).

Abstract

Time-series data are 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 assume 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. The source code is available here: \url{https://github.com/theabrusch/FreqRISE}.

View on arXivView PDF

Code Implementations(1)

theabrusch/FreqRISEOfficial100%
30PythonJul 25, 20241 years ago

Similar Papers

FLEXtime: Filterbank learning to explain time series

84% match1 repo22024

FreqLens: Interpretable Frequency Attribution for Time Series Forecasting

83% match1 repo2026

Explanation Space: A New Perspective into Time Series Interpretability

82% match1 repo42024

Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning

82% match1 repo222024

Robust Explainer Recommendation for Time Series Classification

82% match1 repo72023

Towards Interpretable Time Series Foundation Models

81% match1 repo2025

Cite this paper

@article{brsch2024freqrise,
  title  = {FreqRISE: Explaining time series using frequency masking},
  author = {Thea Brüsch and Kristoffer Knutsen Wickstrøm and Mikkel N. Schmidt and Tommy Sonne Alstrøm and Robert Jenssen},
  year   = {2024},
  eprint = {2406.13584},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.13584v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.13584.svg)](https://codeofpaper.com/paper/2406.13584)

Discussion