APICe » Publications » Agent-Based Explanations in AI: Towards an Abstract Framework

Agent-Based Explanations in AI: Towards an Abstract Framework

Giovanni Ciatto, Michael I. Schumacher, Andrea Omicini, Davide Calvaresi
Recently, the eXplainable AI (XAI) research community has focused on developing methods making Machine Learning (ML) predictors more interpretable or 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, in spite of the sound metaphors that Multi-Agent System (MAS) could easily provide to address such a challenge, an 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.
Keywords: Explainable artificial intelligence; Multi-agent systems; Understandability; Explainability; Interpretability
Explainable, Transparent Autonomous Agents and Multi-Agent Systems, Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence) 12175, pages 3-20, 2020.
Davide Calvaresi, Amro Najjar, Michael Winikoff, Kary Främling (eds.), Springer, Cham
Second International Workshop, EXTRAAMAS 2020, Auckland, New Zealand, May 9–13, 2020, Revised Selected Papers
@incollection{agentbasedxai-extraamas2020,
	Author = {Ciatto, Giovanni and Schumacher, Michael I. and Omicini, Andrea and Calvaresi, Davide},
	Booktitle = {Explainable, Transparent Autonomous Agents and Multi-Agent Systems},
	Doi = {10.1007/978-3-030-51924-7_1},
	IrisId = {11585/7659520},
	Isbn = {978-3-030-51923-0},
	Isbn-Online = {978-3-030-51924-7},
	Editor = {Calvaresi, Davide  and Najjar, Amro and Winikoff, Michael and Främling, Kary},
	Keywords = {Explainable artificial intelligence; Multi-agent systems; Understandability; Explainability; Interpretability},
	Note = {Second International Workshop, EXTRAAMAS 2020, Auckland, New Zealand, May 9–13, 2020, Revised Selected Papers},
	Numpages = 18,
	Pages = {3--20},
	Publisher = {Springer, Cham},
	Series = {Lecture Notes in Computer Science},
	Subseries = {Lecture Notes in Artificial Intelligence},
	Title = {Agent-Based Explanations in {AI}: Towards an Abstract Framework},
	Url = {http://link.springer.com/chapter/10.1007/978-3-030-51924-7_1},
	Volume = 12175,
	Year = 2020}