File(s) under permanent embargo
Simple supervised dissimilarity measure: Bolstering iForest-induced similarity with class information without learning
journal contribution
posted on 2020-08-01, 00:00 authored by Jonathan R Wells, Sunil AryalSunil Aryal, Kai Ming TingExisting distance metric learning methods require optimisation to learn a feature space to transform data—this makes them computationally expensive in large datasets. In classification tasks, they make use of class information to learn an appropriate feature space. In this paper, we present a simple supervised dissimilarity measure which does not require learning or optimisation. It uses class information to measure dissimilarity of two data instances in the input space directly. It is a supervised version of an existing data-dependent dissimilarity measure called e. Our empirical results in k-NN and LVQ classification tasks show that the proposed simple supervised dissimilarity measure generally produces predictive accuracy better than or at least as good as existing state-of-the-art supervised and unsupervised dissimilarity measures.
History
Journal
Knowledge and Information SystemsVolume
62Issue
8Pagination
3203 - 3216Publisher
SpringerLocation
Berlin, GermanyPublisher DOI
ISSN
0219-1377eISSN
0219-3116Language
engPublication classification
C1 Refereed article in a scholarly journalUsage metrics
Categories
Keywords
Science & TechnologyTechnologyComputer Science, Artificial IntelligenceComputer Science, Information SystemsComputer ScienceDistance metric learningSupervised dissimilarity measureData-dependent dissimilarityClass entropyIsolation forestInformation SystemsArtificial Intelligence and Image Processing
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC