Date
2010
Dewey
Intelligence artificielle
Sujet
LP-trees
Conference country
PORTUGAL
Book title
ECAI 2010 19th European Conference on Artificial Intelligence 16–20 August 2010, Lisbon, Portugal - proceedings
Author
Wooldridge, Michael
Publisher
IOS Press
Publisher city
Tokyo
Year
2010
ISBN
978-1-60750-605-8
Author
Booth, Richard
Chevaleyre, Yann
Lang, Jérôme
Mengin, Jérôme
Sombattheera, Chattrakul
Type
Communication / Conférence
Item number of pages
269-274
Abstract (EN)
We consider the problem of learning a user's ordinal preferences on a multiattribute domain, assuming that her preferences are lexicographic. We introduce a general graphical representation called LP-trees which captures various natural classes of such preference relations, depending on whether the importance order between attributes and/or the local preferences on the domain of each attribute is conditional on the values of other attributes. For each class we determine the Vapnik-Chernovenkis dimension, the communication complexity of preference elicitation, and the complexity of identifying a model in the class consistent with a set of user-provided examples.