Preference Elicitation via Theory Refinement

  title={Preference Elicitation via Theory Refinement},
  author={Peter Haddawy and Vu A. Ha and Angelo C. Restificar and Benjamin Geisler and John M. Miyamoto},
  journal={J. Mach. Learn. Res.},
We present an approach to elicitation of user preference models in which assumptions can be used to guide but not constrain the elicitation process. We demonstrate that when domain knowledge is available, even in the form of weak and somewhat inaccurate assumptions, significantly less data is required to build an accurate model of user preferences than when no domain knowledge is provided. This approach is based on the KBANN (Knowledge-Based Artificial Neural Network) algorithm pioneered by… 

Figures from this paper

Reasoning with Conditional Preferences Across Attributes
A structure, a Conditional Outcome Preference Network (COP-network), for modeling preferences directly elicited from a user, which can be easily checked for consistency and redundancy, and used to determine quickly whether one outcome is preferred over another.
Efficient and non-parametric reasoning over user preferences
A novel approach is proposed for generating an ordinal utility function from a set of qualitative preference statements, drawing upon techniques from knowledge representation and machine learning, and results confirm that the new method is effective on real-world data.
Detecting and Adapting to Change in User Preference
This paper introduced two complementary indicators for detecting change in preference which can be used depending on the granularity of observed information and implemented the utility model using knowledge-based artificial neural networks that encode assumptions about a decision maker’s preferences.
Preference Learning
The editors first offer a thorough introduction, including a systematic categorization according to learning task and learning technique, along with a unified notation, and the first half of the book is organized into parts on applications of preference learning in multiattribute domains, information retrieval, and recommender systems.
Knowledge-based acquisition of tradeoff preferences for negotiating agents
It is identified that user trade-off preferences play a fundamental role in negotiation in general and another method is developed to remove the limitation of the high user workload of the exhaustive method.
Acquiring user tradeoff strategies and preferences for negotiating agents: A default-then-adjust method
Elicitating, modeling, and processing uncertain human preferences for software agents in electronic negotiations: An empirical study
The findings indicate that the proposed method is suited for elicitating fuzzy set based preferences, and the fuzzy preference model can project human decisions more accurately than a traditional, crisp approach.
Similarity of personal preferences: Theoretical foundations and empirical analysis
A Survey of Preference Elicitation
The survey explores the potential for integrating preference elicitation techniques into an existing assisted navigation system designed to aid users with data exploration and how the incorporation of preference elicit techniques could potentially benefit the navigation assistant.
Modeling challenges with influence diagrams: Constructing probability and utility models


Toward Case-Based Preference Elicitation: Similarity Measures on Preference Structures
This paper proposes eliciting the preferences of a new user interactively and incrementally, using the closest existing preference structures as potential defaults, and takes the first step of studying various distance measures over fully and partially specified preference structures.
Making Rational Decisions Using Adaptive Utility Elicitation
An algorithm is proposed that interleaves the analysis of the decision problem and utility elicitation to allow these two tasks to inform each other and computes the best strategy based on the information acquired so far.
Interactive Assessment of User Preference Models: The Automated Travel Assistant
The Automated Travel Assistant is presented, an implemented prototype of the model that interactively builds flight itineraries using realtime airline information and has had over 4000 users between May and October 1996.
Intelligent profiling by example
The Apt Decision agent learns user preferences in the domain of rental real estate by observing the user's critique of apartment features, and uses interactive learning techniques to build a profile of user preferences, which can be saved and used in further retrievals.
The Decision-Theoretic Video Advisor*
The DIVA (DecisionTheoretic Interactive Video Advisor) system elicits user preferences using a case-based technique and hard constraints are used to permit the user to communicate temporary deviations from his basic preferences.
Automated refinement of first-order horn-clause domain theories
A system, Forte (First-Order Revision of Theories from Examples from Examples), which refines first-order Horn-clause theories by integrating a variety of different revision techniques into a coherent whole, guided by a global heuristic.
Automated Refinement of First-Order Horn-Clause Domain Theories
A system, forte (First-Order Revision of Theories from Examples from Examples), which refines first-order Horn-clause theories by integrating a variety of different revision techniques into a coherent whole, guided by a global heuristic.
The Lumière Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users
This work reviews work on Bayesian user models that can be employed to infer a user's needs by considering a users' background, actions, and queries and proposes an overall architecture for an intelligent user interface.
Extracting refined rules from knowledge-based neural networks
This article proposes and empirically evaluates a method for the final, and possibly most difficult, step of the refinement of existing knowledge and demonstrates that neural networks can be used to effectively refine symbolic knowledge.
Finding Accurate Frontiers: A Knowledge-Intensive Approach to Relational Learning
An approach to analytic learning is described that searches for accurate entailments of a Horn Clause domain theory by applying a set of operators that derive frontiers from domain theories.