001031802 001__ 1031802
001031802 005__ 20250203133212.0
001031802 0247_ $$2doi$$a10.1109/TQE.2024.3475875
001031802 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-05822
001031802 0247_ $$2WOS$$aWOS:001346704400001
001031802 037__ $$aFZJ-2024-05822
001031802 082__ $$a621.3
001031802 1001_ $$0P:(DE-HGF)0$$aZardini, Enrico$$b0$$eCorresponding author
001031802 245__ $$aLocal Binary and Multiclass SVMs Trained on a Quantum Annealer
001031802 260__ $$aNew York, NY$$bIEEE$$c2024
001031802 3367_ $$2DRIVER$$aarticle
001031802 3367_ $$2DataCite$$aOutput Types/Journal article
001031802 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1730975620_13200
001031802 3367_ $$2BibTeX$$aARTICLE
001031802 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001031802 3367_ $$00$$2EndNote$$aJournal Article
001031802 520__ $$aSupport vector machines (SVMs) are widely used machine learning models, with formulations for both classification and regression tasks. In the last years, with the advent of working quantum annealers, hybrid SVM models characterised by quantum training and classical execution have been introduced. These models have demonstrated comparable performance to their classical counterparts. However, they are limited in the training set size due to the restricted connectivity of the current quantum annealers. Hence, to take advantage of large datasets, a strategy is required. In the classical domain, local SVMs, namely, SVMs trained on the data samples selected by a k -nearest neighbors model, have already proven successful. Here, the local application of quantum-trained SVM models is proposed and empirically assessed. In particular, this approach allows overcoming the constraints on the training set size of the quantum-trained models while enhancing their performance. In practice, the Fast Local Kernel Support Vector Machine (FaLK-SVM) method, designed for efficient local SVMs, has been combined with quantum-trained SVM models for binary and multiclass classification. In addition, for comparison, FaLK-SVM has been interfaced for the first time with a classical single-step multiclass SVM model (CS SVM). Concerning the empirical evaluation, D-Wave's quantum annealers and real-world datasets taken from the remote sensing domain have been employed. The results have shown the effectiveness and scalability of the proposed approach, but also its practical applicability in a real-world large-scale scenario.
001031802 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001031802 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001031802 7001_ $$0P:(DE-Juel1)191384$$aDelilbasic, Amer$$b1
001031802 7001_ $$00000-0001-6524-0601$$aBlanzieri, Enrico$$b2
001031802 7001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b3
001031802 7001_ $$0P:(DE-HGF)0$$aPastorello, Davide$$b4
001031802 773__ $$0PERI:(DE-600)3035782-2$$a10.1109/TQE.2024.3475875$$gp. 1 - 13$$p3103512 $$tIEEE transactions on quantum engineering$$v5$$x2689-1808$$y2024
001031802 8564_ $$uhttps://juser.fz-juelich.de/record/1031802/files/postprint.pdf$$yOpenAccess
001031802 8564_ $$uhttps://juser.fz-juelich.de/record/1031802/files/pre-print.pdf$$yOpenAccess
001031802 8564_ $$uhttps://juser.fz-juelich.de/record/1031802/files/pre-print.gif?subformat=icon$$xicon$$yOpenAccess
001031802 8564_ $$uhttps://juser.fz-juelich.de/record/1031802/files/pre-print.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001031802 8564_ $$uhttps://juser.fz-juelich.de/record/1031802/files/pre-print.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001031802 8564_ $$uhttps://juser.fz-juelich.de/record/1031802/files/pre-print.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001031802 909CO $$ooai:juser.fz-juelich.de:1031802$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001031802 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)191384$$aForschungszentrum Jülich$$b1$$kFZJ
001031802 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b3$$kFZJ
001031802 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001031802 9141_ $$y2024
001031802 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001031802 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001031802 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2023-09-03
001031802 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2023-09-03
001031802 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-12
001031802 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-12
001031802 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-04-03T10:39:05Z
001031802 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-04-03T10:39:05Z
001031802 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-04-03T10:39:05Z
001031802 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-12
001031802 915__ $$0StatID:(DE-HGF)0112$$2StatID$$aWoS$$bEmerging Sources Citation Index$$d2024-12-12
001031802 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-12
001031802 920__ $$lyes
001031802 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001031802 980__ $$ajournal
001031802 980__ $$aVDB
001031802 980__ $$aUNRESTRICTED
001031802 980__ $$aI:(DE-Juel1)JSC-20090406
001031802 9801_ $$aFullTexts