Publication:
EXPECTATION: Personalized explainable artificial intelligence for decentralized agents with heterogeneous knowledge

dc.contributor.authorCalvaresi, D.
dc.contributor.authorCiatto, G.
dc.contributor.authorNajjar, A.
dc.contributor.authorAydoğan, Reyhan
dc.contributor.authorVan der Torre, L.
dc.contributor.authorOmicini, A.
dc.contributor.authorSchumacher, M.
dc.contributor.departmentComputer Science
dc.contributor.ozuauthorAYDOĞAN, Reyhan
dc.date.accessioned2023-04-10T07:32:38Z
dc.date.available2023-04-10T07:32:38Z
dc.date.issued2021
dc.description.abstractExplainable AI (XAI) has emerged in recent years as a set of techniques and methodologies to interpret and explain machine learning (ML) predictors. To date, many initiatives have been proposed. Nevertheless, current research efforts mainly focus on methods tailored to specific ML tasks and algorithms, such as image classification and sentiment analysis. However, explanation techniques are still embryotic, and they mainly target ML experts rather than heterogeneous end-users. Furthermore, existing solutions assume data to be centralised, homogeneous, and fully/continuously accessible—circumstances seldom found altogether in practice. Arguably, a system-wide perspective is currently missing. The project named “Personalized Explainable Artificial Intelligence for Decentralized Agents with Heterogeneous Knowledge ” (Expectation) aims at overcoming such limitations. This manuscript presents the overall objectives and approach of the Expectation project, focusing on the theoretical and practical advance of the state of the art of XAI towards the construction of personalised explanations in spite of decentralisation and heterogeneity of knowledge, agents, and explainees (both humans or virtual). To tackle the challenges posed by personalisation, decentralisation, and heterogeneity, the project fruitfully combines abstractions, methods, and approaches from the multi-agent systems, knowledge extraction/injection, negotiation, argumentation, and symbolic reasoning communities.en_US
dc.description.sponsorshipSwiss National Science Foundation (SNSF) ; Ministry of Education, Universities and Research (MIUR) ; Luxembourg National Research Fund ; TÜBİTAK
dc.identifier.doi10.1007/978-3-030-82017-6_20en_US
dc.identifier.endpage343en_US
dc.identifier.isbn978-303082016-9
dc.identifier.issn0302-9743en_US
dc.identifier.scopus2-s2.0-85113351710
dc.identifier.startpage331en_US
dc.identifier.urihttp://hdl.handle.net/10679/8113
dc.identifier.urihttps://doi.org/10.1007/978-3-030-82017-6_20
dc.identifier.volume12688 LNAIen_US
dc.identifier.wos000691781800020
dc.language.isoengen_US
dc.publicationstatusPublisheden_US
dc.publisherSpringeren_US
dc.relationinfo:eu-repo/grantAgreement/TUBITAK/1001 - Araştırma/120N680
dc.relation.ispartofEXTRAAMAS 2021: Explainable and Transparent AI and Multi-Agent Systems
dc.relation.publicationcategoryInternational
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsChist-Era IVen_US
dc.subject.keywordsDecentralisationen_US
dc.subject.keywordsExpectationen_US
dc.subject.keywordseXplanable AIen_US
dc.subject.keywordsMulti-agent systemsen_US
dc.subject.keywordsPersonalisationen_US
dc.titleEXPECTATION: Personalized explainable artificial intelligence for decentralized agents with heterogeneous knowledgeen_US
dc.typeConference paperen_US
dspace.entity.typePublication
relation.isOrgUnitOfPublication85662e71-2a61-492a-b407-df4d38ab90d7
relation.isOrgUnitOfPublication.latestForDiscovery85662e71-2a61-492a-b407-df4d38ab90d7

Files

License bundle

Now showing 1 - 1 of 1
Placeholder
Name:
license.txt
Size:
1.45 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections