Post-hoc Global Explanation using Hypersphere Sets

Kohei Asano, Jinhee Chun

2022

Abstract

We propose a novel global explanation method for a pre-trained machine learning model. Generally, machine learning models behave as a black box. Therefore, developing a tool that reveals a model’s behavior is important. Some studies have addressed this issue by approximating a black-box model with another interpretable model. Although such a model summarizes a complex model, it sometimes provides incorrect explanations because of a gap between the complex model. We define hypersphere sets of two types that respectively approximate a model based on recall and precision metrics. A high-recall set of hyperspheres provides a summary of a black-box model. A high-precision one describes the model’s behavior precisely. We demonstrate from experimentation that the proposed method provides a global explanation for an arbitrary black-box model. Especially, it improves recall and precision metrics better than earlier methods.

Paper Citation

in Harvard Style

Asano K. and Chun J. (2022). Post-hoc Global Explanation using Hypersphere Sets. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 236-243. DOI: 10.5220/0010819100003116

in Bibtex Style

@conference{icaart22,
author={Kohei Asano and Jinhee Chun},
title={Post-hoc Global Explanation using Hypersphere Sets},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={236-243},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010819100003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Post-hoc Global Explanation using Hypersphere Sets
SN - 978-989-758-547-0
AU - Asano K.
AU - Chun J.
PY - 2022
SP - 236
EP - 243
DO - 10.5220/0010819100003116