Agent-Based Explanations in AI : towards an abstract framework

Ciatto, Giovanni (University of Bologna, Cesena, Italy) ; Schumacher, Michael (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Omicini, Andrea (University of Bologna, Cesena, Italy) ; Calvaresi, Davide (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis))

Recently, the eXplainable AI (XAI) research community has focused on developing methods making Machine Learning (ML) predictors more interpretable and explainable. Unfortunately, researchers are struggling to converge towards an unambiguous definition of notions such as interpretation, or, explanation—which are often (and mistakenly) used interchangeably. Furthermore, despite the sound metaphors that Multi-Agent System (MAS) could easily provide to address such a challenge, and agent-oriented perspective on the topic is still missing. Thus, this paper proposes an abstract and formal framework for XAI-based MAS, reconciling notions, and results from the literature.


Note: Due to the COVID-19 outbreak, the EXTRAAMAS: International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systemsvenue in Auckland was cancelled. The proceedings of the online conference are however published according to the original schedule.


Keywords:
Conference Type:
published full paper
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Publisher:
Auckland, New Zealand, 9-13 May 2020
Date:
2020-05
Auckland, New Zealand
9-13 May 2020
Pagination:
Pp. 3-20
Published in:
Proceedings of the EXTRAAMAS: International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems 2020
Series Statement:
Lecture Notes in Computer Science, vol. 12175
DOI:
ISBN:
978-3-030-51923-0
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2020-11-16, last modified 2020-11-20

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)