Post-hoc explanation using a mimic rule for numerical data

Kohei Asano, Jinhee Chun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a novel rule-based explanation method for an arbitrary pre-trained machine learning model. Generally, machine learning models make black-box decisions that are not easy to explain the logical reasons to derive them. Therefore, it is important to develop a tool that gives reasons for the model's decision. Some studies have tackled the solution of this problem by approximating an explained model with an interpretable model. Although these methods provide logical reasons for a model's decision, a wrong explanation sometimes occurs. To resolve the issue, we define a rule model for the explanation, called a mimic rule, which behaves similarly in the model in its region. We obtain a mimic rule that can explain the large area of the numerical input space by maximizing the region. Through experimentation, we compare our method to earlier methods. Then we show that our method often improves local fidelity.

Original languageEnglish
Title of host publicationICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence
EditorsAna Paula Rocha, Luc Steels, Jaap van den Herik
PublisherSciTePress
Pages768-774
Number of pages7
ISBN (Electronic)9789897584848
Publication statusPublished - 2021
Event13th International Conference on Agents and Artificial Intelligence, ICAART 2021 - Virtual, Online
Duration: 2021 Feb 42021 Feb 6

Publication series

NameICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence
Volume2

Conference

Conference13th International Conference on Agents and Artificial Intelligence, ICAART 2021
CityVirtual, Online
Period21/2/421/2/6

Keywords

  • Explanations
  • Rules
  • Transparency

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint Dive into the research topics of 'Post-hoc explanation using a mimic rule for numerical data'. Together they form a unique fingerprint.

Cite this