TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models
Abstract
Time series forecasting is a demanding task ranging from weather to failure forecasting with black-box models achieving state-of-the-art performances. However, understanding and debugging are not guaranteed. We propose TS-MULE, a local surrogate model explanation method specialized for time series extending the LIME approach. Our extended LIME works with various ways to segment and perturb the time series data. In our extension, we present six sampling segmentation approaches for time series to improve the quality of surrogate attributions and demonstrate their performances on three deep learning model architectures and three common multivariate time series datasets.
Cite
@article{arxiv.2109.08438,
title = {TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models},
author = {Udo Schlegel and Duy Vo Lam and Daniel A. Keim and Daniel Seebacher},
journal= {arXiv preprint arXiv:2109.08438},
year = {2021}
}
Comments
8 pages, 2 pages references, Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI) at ECML/PKDD 2021