Eliminating the impossible, whatever remains must be true: On extracting and applying background knowledge in the context of formal explanations

Jinqiang Yu, Alexey Ignatiev, Peter J. Stuckey, Nina Narodytska, Joao Marques-Silva

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

10 Citations (Scopus)

Abstract

The rise of AI methods to make predictions and decisions has led to a pressing need for more explainable artificial intelligence (XAI) methods. One common approach for XAI is to produce a post-hoc explanation, explaining why a black box ML model made a certain prediction. Formal approaches to post-hoc explanations provide succinct reasons for why a prediction was made, as well as why not another prediction was made. But these approaches assume that features are independent and uniformly distributed. While this means that “why” explanations are correct, they may be longer than required. It also means the “why not” explanations may be suspect as the counterexamples they rely on may not be meaningful. In this paper, we show how one can apply background knowledge to give more succinct “why” formal explanations, that are presumably easier to interpret by humans, and give more accurate “why not” explanations. In addition, we show how to use existing rule induction techniques to efficiently extract background information from a dataset.

Original languageEnglish
Title of host publicationProceedings of the 37th AAAI Conference on Artificial Intelligence
EditorsBrian Williams, Yiling Chen, Jennifer Neville
Place of PublicationWashington DC USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Pages4123-4131
Number of pages9
ISBN (Electronic)9781577358800
DOIs
Publication statusPublished - 2023
EventAAAI Conference on Artificial Intelligence 2023 - Washington, United States of America
Duration: 7 Feb 202314 Feb 2023
Conference number: 37th
https://aaai-23.aaai.org (Website)
https://ojs.aaai.org/index.php/AAAI/index (Proceedings)

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAAAI Press
Volume37
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

ConferenceAAAI Conference on Artificial Intelligence 2023
Abbreviated titleAAAI 2023
Country/TerritoryUnited States of America
CityWashington
Period7/02/2314/02/23
Internet address

Cite this