NASA Jet Propulsion Laboratory California Institute of Technology Follow this link to skip to the main content

BEACON eSpace at Jet Propulsion Laboratory >
JPL Technical Report Server >
JPL TRS 1992+ >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2014/39687

Title: Learning user preferences for sets of objects
Authors: Wagstaff, Kiri L.
desJardins, Marie
Eaton, Eric
Keywords: preferences
subset selections
Issue Date: 25-Jun-2006
Publisher: Pasadena, CA : Jet Propulsion Laboratory, National Aeronautics and Space Administration, 2006.
Citation: 23rd International Conference on Machine Learning, Pittsburgh, Pennsylvania , June 25-59, 2006.
Abstract: Most work on preference learning has focused on pairwise preferences or rankings over individual items. In this paper, we present a method for learning preferences over sets of items. Our learning method takes as input a collection of positive examples—that is, one or more sets that have been identified by a user as desirable. Kernel density estimation is used to estimate the value function for individual items, and the desired set diversity is estimated from the average set diversity observed in the collection. Since this is a new learning problem, we introduce a new evaluation methodology and evaluate the learning method on two data collections: synthetic blocks-world data and a new real-world music data collection that we have gathered.
URI: http://hdl.handle.net/2014/39687
Appears in Collections:JPL TRS 1992+

Files in This Item:

File Description SizeFormat
06-1230.pdf266 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, but are furnished with U.S. government purpose use rights.

 

Privacy/Copyright Image Policy Beacon Home Contact Us
NASA Home Page + Div 27
+ JPL Space
Site last updated on November 15, 2012.
If you have any comments or suggestions for this web site, please e-mail Alexander Smith or call 4-4202.