Learning preference relations over combinatorial domains

We address the problem of learning preference relations over multiattribute(or combinatorial) domains. We do so by making hypotheses about thedependence structure between attributes that the preference relation enjoys. Thefirst hypothesis we consider is the simplest one, namely, separability (no dependencesbetween attributes: the preference over the values of each attribute is independentof the values of other attributes); then we consider the more general casewhere the dependence structure takes the form of an acyclic graph. In all cases,what we want to learn is a set of local preference relations (or equivalently, a CPnet)rather than a fully specified preference relation. We consider three forms ofconsistency between a CP-net and a set of examples, and for two of them we givean exact characterization in the case of separability, as well as complexity results.

[1]  Nic Wilson,et al.  Consistency and Constrained Optimisation for Conditional Preferences , 2004, ECAI.

[2]  Paolo Viappiani,et al.  Preference-based Search using Example-Critiquing with Suggestions , 2006, J. Artif. Intell. Res..

[3]  Boi Faltings,et al.  Evaluating Preference-based Search Tools: A Tale of Two Approaches , 2006, AAAI.

[4]  Bradley N. Miller,et al.  MovieLens unplugged: experiences with an occasionally connected recommender system , 2003, IUI '03.

[5]  John B. Kidd,et al.  Decisions with Multiple Objectives—Preferences and Value Tradeoffs , 1977 .

[6]  Li Chen,et al.  Survey of Preference Elicitation Methods , 2004 .

[7]  R. L. Keeney,et al.  Decisions with Multiple Objectives: Preferences and Value Trade-Offs , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Peter Haddawy,et al.  Problem-Focused Incremental Elicitation of Multi-Attribute Utility Models , 1997, UAI.

[9]  Jörg P. Müller,et al.  Learning User Preferences for Multi-attribute Negotiation: An Evolutionary Approach , 2003, CEEMAS.

[10]  Ralph L. Keeney,et al.  Decision Analysis with Multiple Conflicting Objectives, Preferences and Value Tradeoffs , 1975 .

[11]  Ronen I. Brafman,et al.  Introducing Variable Importance Tradeoffs into CP-Nets , 2002, UAI.

[12]  Patrice Perny,et al.  Preference-based Search and Machine Learning for Collaborative Filtering: the "Film-Conseil" Movie Recommender System , 2001 .

[13]  Ronen I. Brafman,et al.  CP-nets: A Tool for Representing and Reasoning withConditional Ceteris Paribus Preference Statements , 2011, J. Artif. Intell. Res..

[14]  Ronen I. Brafman,et al.  CP-nets: Reasoning and Consistency Testing , 2002, KR.