| Monday, 15
September |
|
| 14:00-14:40 |
Eyke Hüllermeier: Machine Learning Methods for
Preference Elicitation: An Overview |
| 14:40-15:20 |
Johannes Fürnkranz, Eyke Hüllermeier: Pairwise Preference Learning and Ranking |
| 15:20-16:00 |
Klaus Brinker: Active Learning of Ranking Functions |
| 16:00-16:30 |
Kaffeepause |
| 16:30-17:10 |
Bernd Freisleben, Thomas Friese: Preference Learning in Internet Collaboration Environments |
| 17:10-17:50 |
Jan-Hendrik Dörner: Weighting Predictors in Memory-based Collaborative Filtering |
| 17:50-18:30 | Björn Fiehn, Jörg
Müller: A framework for
user-adaptive
matchmaking |
The preferences of an individual, say, the participant of an electronic auction or the customer of an electronic store, can be expressed in various ways, either explicitly, e.g. in the form of preference statements or implicitly, e.g. through the way of acting in different situations. The problem of finding out about an individual's preferences, or about those of a group of individuals, is referred to as preference elicitation. This requires, among other things, formal models for representing preferences and methods for their (automatic) acquisition. Touching on various aspects of AI, both theoretical and practical, preference elicitation is one of this field's most recent and interesting research topics.
The focus of the workshop will be on learning methods for preference elicitation, that is on methods for inducing preferences from given observations. Like other types of complex learning tasks that have recently entered the stage in machine learning and related fields, preference learning deviates strongly from the standard problems of classification and regression. It is particularly challenging as it involves the prediction of complex structures, such as weak or partial order relations, rather than single values. Moreover, training input will not, as is usually the case, be offered in the form of complete examples but may comprise more general types of information, such as relative preferences or different kinds of indirect feedback.
Apart from posing challenging theoretical problems, preference learning is highly relevant from a practical point of view. As an example, consider the important application of autonomous (web) agents performing various tasks on the net, such as acting on behalf of a user in electronic commerce or recommending decisions to users in collaborative filtering. Following modern AI’s major paradigm of a rational agent, ideas and concepts from decision theory, including formal models of preferences, often serve as a theoretical basis for implementing such agents. Since an agent recommending decisions or acting on behalf of a user should clearly reflect that user's preferences, the formal modeling as well as the automatic learning, discovery and adaptation of preferences can be considered an essential aspect of autonomous agent design.
The workshop is intended as a discussion forum for both, researchers in machine learning (including related fields such as statistics and data mining) and potential users of preference elicitation techniques in all areas of AI. Topics of interest include, but are not limited to: preference modeling, learning methods for preference elicitation, extensions of the common frameworks for machine learning (supervised, unsupervised and reinforcement learning), applications of preference elicitation in various fields, e.g. in electronic commerce, personalization, collaborative filtering, decision and game theory, autonomous/software/web agents, information retrieval, knowledge representation, negotiation, user modeling, and web intelligence.
Contact:Eyke Hüllermeier,
FB Mathematik und Informatik,
Philipps-Universität Marburg, Lahnberge,
D-35032 Marburg