dc.contributor.author | Dimopoulos, Yannis | en |
dc.contributor.author | Michael, Loizos | en |
dc.contributor.author | Athienitou, F. | en |
dc.creator | Dimopoulos, Yannis | en |
dc.creator | Michael, Loizos | en |
dc.creator | Athienitou, F. | en |
dc.date.accessioned | 2019-11-13T10:39:54Z | |
dc.date.available | 2019-11-13T10:39:54Z | |
dc.date.issued | 2009 | |
dc.identifier.isbn | 978-1-57735-426-0 | |
dc.identifier.uri | http://gnosis.library.ucy.ac.cy/handle/7/53866 | |
dc.description.abstract | CP-networks have been proposed as a simple and intuitive graphical tool for representing conditional ceteris paribus preference statements over the values of a set of variables. While the problem of reasoning with CP-networks has been receiving some attention, there are very few works that address the problem of learning CP-networks. In this work we investigate the task of learning CP-networks, given access to a set of pairwise comparisons. We first prove that the learning problem is intractable, even under several simplifying assumptions. We then present an algorithm that, under certain assumptions about the observed pair-wise comparisons, identifies a CP-network that entails these comparisons. We finally show that the proposed algorithm is a PAC-learner, and, thus, that the CP-networks it induces accurately predict the user's preferences on previously unseen situations. | en |
dc.source | IJCAI International Joint Conference on Artificial Intelligence | en |
dc.source | 21st International Joint Conference on Artificial Intelligence, IJCAI-09 | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-77956048811&partnerID=40&md5=0447939ea9debc68933b943a4300c7e2 | |
dc.subject | Algorithms | en |
dc.subject | Artificial intelligence | en |
dc.subject | Simplifying assumptions | en |
dc.subject | CP-networks | en |
dc.subject | Preference elicitation | en |
dc.subject | Preference statements | en |
dc.subject | Graphical tools | en |
dc.subject | Learning problem | en |
dc.subject | Pair-wise comparison | en |
dc.title | Ceteris paribus preference elicitation with predictive guarantees | en |
dc.type | info:eu-repo/semantics/conferenceObject | |
dc.description.startingpage | 1890 | |
dc.description.endingpage | 1895 | |
dc.author.faculty | 002 Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied Sciences | |
dc.author.department | Τμήμα Πληροφορικής / Department of Computer Science | |
dc.type.uhtype | Conference Object | en |
dc.description.notes | <p>Sponsors: Int. Jt. Conf. Artif. Intell. (IJCAI) | en |
dc.description.notes | Association for the Advancement of Artificial Intelligence (AAAI) | en |
dc.description.notes | USC Institute for Creative Technologies | en |
dc.description.notes | National Science Foundation | en |
dc.description.notes | Microsoft Research | en |
dc.description.notes | Conference code: 83585 | en |
dc.description.notes | Cited By :22</p> | en |
dc.contributor.orcid | Dimopoulos, Yannis [0000-0001-9583-9754] | |
dc.gnosis.orcid | 0000-0001-9583-9754 | |