Explaining Reject Options of Learning Vector Quantization Classifiers

André Artelt, André Artelt, Johannes Brinkrolf, Roel Visser, Barbara Hammer

2022

Abstract

While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptably low certainty would be possible. With the ongoing rise of eXplainable AI, a lot of methods for explaining model predictions have been developed. However, understanding why a given input was rejected, instead of being classified by the model, is also of interest. Surprisingly, explanations of rejects have not been considered so far. We propose to use counterfactual explanations for explaining rejects and investigate how to efficiently compute counterfactual explanations of different reject options for an important class of models, namely prototype-based classifiers such as learning vector quantization models.

Paper Citation

in Harvard Style

Artelt A., Brinkrolf J., Visser R. and Hammer B. (2022). Explaining Reject Options of Learning Vector Quantization Classifiers. In Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA; ISBN 978-989-758-611-8, SciTePress, pages 249-261. DOI: 10.5220/0011389600003332

in Bibtex Style

@conference{ncta22,
author={André Artelt and Johannes Brinkrolf and Roel Visser and Barbara Hammer},
title={Explaining Reject Options of Learning Vector Quantization Classifiers},
booktitle={Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA},
year={2022},
pages={249-261},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011389600003332},
isbn={978-989-758-611-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA
TI - Explaining Reject Options of Learning Vector Quantization Classifiers
SN - 978-989-758-611-8
AU - Artelt A.
AU - Brinkrolf J.
AU - Visser R.
AU - Hammer B.
PY - 2022
SP - 249
EP - 261
DO - 10.5220/0011389600003332
PB - SciTePress