Reference : Using Class-probability Models instead of Hard Classifiers as Base Learners in the Ra...
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/87250
Using Class-probability Models instead of Hard Classifiers as Base Learners in the Ranking by Pairwise Comparison Algorithm
English
Hiard, Samuel mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore) >]
Wehenkel, Louis mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Feb-2011
ICMLC 2011 3rd International Conference on Machine Learning and Computing Volume 1
Thatcher, Steve
IEEE
218-222
No
No
978-1-4244-9252-7
Chengdu
China
3rd International Conference on Machine Learning and Computing
du 26 février 2011 au 28 février 2011
International Association of Computer Science and Information Technology
Singapour
Singapour
[en] Preference ; class-probability ; models ; robustness
[en] In the field of Preference Learning, the Ranking by Pairwise Comparison algorithm (RPC) consists of using the learning sample to derive pairwise comparators for each possible pair of class labels, and then aggregating the predictions of the whole set of pairwise comparators for a given object in order to produce a global ranking of the class labels. In its standard form, RPC uses hard binary classifiers assigning an integer (0/1) score to each class concerned by a pairwise comparison. In the present work, we compare this setting with a modified version of RPC, where soft binary class-probability models replace the binary classifiers. To this end, we compare ensembles of extremely randomized classprobability estimation trees with ensembles of extremely randomized classification trees. We empirically show that both approaches lead to equivalent results in terms of Spearman’s rho value when using the optimal settings of their metaparameters. However, we also show that in the context of small and noisy datasets (e.g. with partial ranking information) the use of class-probability models is more robust with respect to variations of its meta-parameter values than the hard classifier ensembles. This suggests that using (soft) class-probability comparators is a sensible option in the context of RPC approaches.
Montefiore
Ulg
Researchers ; Professionals
http://hdl.handle.net/2268/87250
Abstracting is permitted with credit to the source. Libraries are permitted to photocopy beyond the limit of U.S. copyright law for private use of patrons those articles in this volume that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923. For other copying, reprint or republication permission, write to IEEE Copyrights Manager, IEEE Operations Center, 445 Hoes Lane, P.O. Box 1331, Piscataway, NJ 08855-1331

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Restricted access
ICMLC_2011_L071.pdfAuthor postprint124.9 kBRequest copy

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.