Understanding Unsupervised Learning Explanations Using Contextual Importance and Utility

Avleen Malhi*, Vlad Apopei, Kary Främling

*Corresponding author for this work

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

Abstract

While the concept of Explainability has advanced significantly in the past decade, many areas remain unexplored. Although XAI implementations have historically been employed in attempting to ‘open’ the traditional black-box model of supervised learning implementation aiming to extract human-understandable information, there are no successful attempts at tackling unsupervised learning. This paper aims to tackle the challenge of using an XAI approach, specifically Contextual Importance and Utility (CIU), in order to provide an explainability layer for unsupervised learning models. The paper introduces the current XAI approaches of CIU as well as the other state-of-the-art implementations such as Lime or Shapley. The challenges posed by the unsupervised learning problem are explored and discussed, both on a conceptual and technical level. A relatively novel approach using a CIU implementation on unsupervised clustering techniques is presented along with the brief comparison with another state-of-the-art method called LIME.

Original languageEnglish
Title of host publicationExplainable Artificial Intelligence - 1st World Conference, xAI 2023, 2023, Proceedings
EditorsLuca Longo
PublisherSpringer
Pages606-617
Number of pages12
ISBN (Print)978-3-031-44063-2
DOIs
Publication statusPublished - 2023
MoE publication typeA4 Conference publication
EventWorld Conference on eXplainable Artificial Intelligence - Lisbon, Portugal
Duration: 26 Jul 202328 Jul 2023
Conference number: 1

Publication series

NameCommunications in Computer and Information Science
Volume1901 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceWorld Conference on eXplainable Artificial Intelligence
Abbreviated titlexAI
Country/TerritoryPortugal
CityLisbon
Period26/07/202328/07/2023

Keywords

  • Contextual importance and utility
  • Explainability
  • Machine learning
  • Unsupervised learning

Fingerprint

Dive into the research topics of 'Understanding Unsupervised Learning Explanations Using Contextual Importance and Utility'. Together they form a unique fingerprint.

Cite this