@misc{10481/84523,
year = {2023},
month = {6},
url = {https://hdl.handle.net/10481/84523},
abstract = {Machine learning approaches have enabled increasingly powerful time series classifiers. While
performance has improved drastically, the resulting classifiers generally suffer from poor
explainability, limiting their applicability in critical areas. Saliency-based methods designed
to highlight the critical features are one of the most promising approaches to improving this
explainability. Here, current techniques commonly rely on artificially perturbing the features,
using, for example, random noise or ‘zeroing’ these features. We first demonstrate that an
important drawback of these methods is that the perturbations used can result in unrealistic
assessments of the classifier, since the perturbations force the data outside their original
distribution. We articulate how this can result in poor identification of critical features, and
hence misleading explanations. In order to address this issue and identify the most important
features for the output of a black-box model, we propose a dual approach through meaningful
perturbation and optimisation. First, leveraging a mechanism originally proposed in image
analysis, a generative model is trained to create within-distribution perturbations of the input.
These are then used to reliably evaluate whether a set of features is critical. Second, a greedybased
segmentation and identification strategy is proposed to search for the smallest set of critical
features. Experiments show that the proposed approach addresses the out-of-distribution problem
and identifies fewer critical features than existing methods. In combination, both aspects of
the proposed approach offer a qualitative advance towards generating meaningful and robust
explanations in the context of time series classification.},
organization = {University of Nottingham and the China Scholarship Council (CSC) from the Ministry of Education
of P.R. China},
organization = {A-TIC-434-UGR20},
organization = {PID2020-119478GB-I00},
publisher = {Elsevier},
keywords = {Time series classification},
keywords = {Post-hoc explanation},
keywords = {Perturbation method},
keywords = {Optimisation approach},
title = {Explaining time series classifiers through meaningful perturbation and optimisation},
doi = {10.1016/j.ins.2023.119334},
author = {Meng, Han and Wagner, Christian and Triguero Velázquez, Isaac},
}