Towards Semantic Description of Explainable Machine Learning Workflows

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

1 Citation (Scopus)
99 Downloads (Pure)

Abstract

Machine learning (ML) has outperformed humans in many areas, and that is why it has been adopted by a large variety of applications, such as computer vision, speech recognition, and robotics. However, their functioning and the reason why they generated specific results usually are not clear to the user, being often considered as black-boxes. Explainable Artificial Intelligence (XAI) aims to make AI systems results better understandable to humans, enabling the optimization of the learning models and trust by users. Semantic Web Technologies (SWT) has been applied to ML models because they provide semantically interpretable tools and allow reasoning on knowledge bases that can help explain ML systems. Nevertheless, current solutions usually limit their explanations to the logic of the results, lacking the description or explanations of the other steps of the ML process, which can restrict the understanding experience of the user, making it difficult to identify in which step corrections and adjustments should take place. In this paper, we give an overview of XAI and SWT, and discuss the importance of providing a holistic solution, by means of an ontology. This challenge has to be addressed to improve understandability of the whole ML process and explanation process.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 25th International Enterprise Distributed Object Computing Conference Workshops, EDOCW 2021
PublisherIEEE
Pages236-244
Number of pages9
ISBN (Electronic)9781665444880
DOIs
Publication statusPublished - 1 Dec 2021
EventIEEE 25th International Enterprise Distributed Object Computing Workshop, EDOCW 2021 - Gold Coast, Australia, Virtual Event, Australia
Duration: 25 Oct 202129 Oct 2021
Conference number: 25

Publication series

NameProceedings - IEEE International Enterprise Distributed Object Computing Workshop, EDOCW
ISSN (Print)1541-7719

Conference

ConferenceIEEE 25th International Enterprise Distributed Object Computing Workshop, EDOCW 2021
Abbreviated titleEDOCW 2021
Country/TerritoryAustralia
CityVirtual Event
Period25/10/2129/10/21

Keywords

  • Machine Learning
  • Ontology
  • Semantic Web Technologies
  • XAI
  • 22/1 OA procedure

Fingerprint

Dive into the research topics of 'Towards Semantic Description of Explainable Machine Learning Workflows'. Together they form a unique fingerprint.

Cite this