Skip navigation
Skip navigation

Kernels and distances for structured data

Gaertner, Thomas; Lloyd, John; Flach, Peter

Description

This paper brings together two strands of machine learning of increasing importance: kernel methods and highly structured data. We propose a general method for constructing a kernel following the syntactic structure of the data, as defined by its type signature in a higher-order logic. Our main theoretical result is the positive definiteness of any kernel thus defined. We report encouraging experimental results on a range of real-world data sets. By converting our kernel to a distance...[Show more]

dc.contributor.authorGaertner, Thomas
dc.contributor.authorLloyd, John
dc.contributor.authorFlach, Peter
dc.date.accessioned2015-12-13T22:50:16Z
dc.identifier.issn0885-6125
dc.identifier.urihttp://hdl.handle.net/1885/80719
dc.description.abstractThis paper brings together two strands of machine learning of increasing importance: kernel methods and highly structured data. We propose a general method for constructing a kernel following the syntactic structure of the data, as defined by its type signature in a higher-order logic. Our main theoretical result is the positive definiteness of any kernel thus defined. We report encouraging experimental results on a range of real-world data sets. By converting our kernel to a distance pseudo-metric for 1-nearest neighbour, we were able to improve the best accuracy from the literature on the Diterpene data set by more than 10%.
dc.publisherKluwer Academic Publishers
dc.sourceMachine Learning
dc.subjectKeywords: High-order logics; Inductive logic programming; Instance-based learning; Kernel methods; Structured data; Data mining; Formal logic; Learning systems; Logic programming; Principal component analysis; Semantics; Syntactics; Transfer functions; Vectors; Dat Higher-order logic; Inductive logic programming; Instance-based learning; Kernel methods; Structured data
dc.titleKernels and distances for structured data
dc.typeJournal article
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.citationvolume57
dc.date.issued2004
local.identifier.absfor080299 - Computation Theory and Mathematics not elsewhere classified
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.ariespublicationMigratedxPub8985
local.type.statusPublished Version
local.contributor.affiliationGaertner, Thomas, Fraunhofer Institute
local.contributor.affiliationLloyd, John, College of Engineering and Computer Science, ANU
local.contributor.affiliationFlach, Peter, University of Bristol
local.description.embargo2037-12-31
local.bibliographicCitation.startpage205
local.bibliographicCitation.lastpage232
local.identifier.doi10.1023/B:MACH.0000039777.23772.30
dc.date.updated2015-12-11T10:39:28Z
local.identifier.scopusID2-s2.0-4444288656
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Gaertner_Kernels_and_distances_for_2004.pdf235.35 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator