Efficiently learning the preferences of people

• Published in: Machine learning Vol. 90; no. 1; pp. 1 - 28
• Main Authors: Birlutiu, Adriana, Groot, Perry, Heskes, Tom
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.01.2013; Springer; Springer Nature B.V
• Subjects: Applied sciences; Artificial Intelligence; Computer Science; Computer science; control theory; systems; Control; Data processing. List processing. Character string processing; Exact sciences and technology; Formalism; Labelling; Learning; Learning and adaptive systems; Mechatronics; Memory organisation. Data processing; Natural Language Processing (NLP); Optimization; Queries; Robotics; Simulation and Modeling; Software; Training; Learning preferences; Active learning; Experimental design; Multi-task learning; Hierarchical modeling; Hierarchical classification; Labelling; Inductive learning; Optimization; Knowledge transfer; Hierarchic relation; Multithread; Active system; Supervised learning; Preference; Learning algorithm
• ISSN: 0885-6125; 1573-0565
• DOI: 10.1007/s10994-012-5297-4

This paper presents a framework for optimizing the preference learning process. In many real-world applications in which preference learning is involved the available training data is scarce and obtaining labeled training data is expensive. Fortunately in many of the preference learning situations data is available from multiple subjects. We use the multi-task formalism to enhance the individual training data by making use of the preference information learned from other subjects. Furthermore, since obtaining labels is expensive, we optimally choose which data to ask a subject for labelling to obtain the most of information about her/his preferences. This paradigm—called active learning—has hardly been studied in a multi-task formalism. We propose an alternative for the standard criteria in active learning which actively chooses queries by making use of the available preference data from other subjects. The advantage of this alternative is the reduced computation costs and reduced time subjects are involved. We validate empirically our approach on three real-world data sets involving the preferences of people.