File(s) under permanent embargo
Virtual attribute subsetting
conference contribution
posted on 2023-05-23, 03:36 authored by Horton, MP, Cameron-Jones, RM, Williams, RNAttribute subsetting is a meta-classification technique, based on learning multiple base-level classifiers on projections of the training data. In prior work with nearest-neighbour base classifiers, attribute subsetting was modified to learn only one classifier, then to selectively ignore attributes at classification time to generate multiple predictions. In this paper, the approach is generalized to any type of base classifier. This ‘virtual attribute subsetting’ requires a fast subset choice algorithm; one such algorithm is found and described. In tests with three different base classifier types, virtual attribute subsetting is shown to yield some or all of the benefits of standard attribute subsetting while reducing training time and storage requirements.
History
Publication title
AI 2006: Advances in Artificial Intelligence 19th Australian Joint Conference on Artificial IntelligenceVolume
19Editors
A Sattar & B KangPagination
214-223ISBN
3-540-49787-0Department/School
School of Information and Communication TechnologyPublisher
Springer-VerlagPlace of publication
Berlin, GermanyEvent title
AJCAIEvent Venue
Hobart, TasmaniaDate of Event (Start Date)
2006-12-04Date of Event (End Date)
2006-12-08Rights statement
Copyright 2006 Springer-Verlag Berlin HeidelbergRepository Status
- Restricted