Jensen-Shannon divergence is a symmetrised, smoothed version of Küllback-Leibler. It has been shown to be the square of a proper distance metric, and has other properties which make it an excellent choice for many high-dimensional spaces in R*. The metric as defined is however expensive to evaluate. In sparse spaces over many dimensions the Intrinsic Dimensionality of the metric space is typically very high, making similarity-based indexing ineffectual. Exhaustive searching over large data collections may be infeasible. Using a property that allows the distance to be evaluated from only those dimensions which are non-zero in both arguments, and through the identification of a threshold function, we show that the cost of the function can be dramatically reduced. © 2013 Springer-Verlag.
Evaluation of Jensen-Shannon distance over sparse data
Cardillo FA;Rabitti F
2013
Abstract
Jensen-Shannon divergence is a symmetrised, smoothed version of Küllback-Leibler. It has been shown to be the square of a proper distance metric, and has other properties which make it an excellent choice for many high-dimensional spaces in R*. The metric as defined is however expensive to evaluate. In sparse spaces over many dimensions the Intrinsic Dimensionality of the metric space is typically very high, making similarity-based indexing ineffectual. Exhaustive searching over large data collections may be infeasible. Using a property that allows the distance to be evaluated from only those dimensions which are non-zero in both arguments, and through the identification of a threshold function, we show that the cost of the function can be dramatically reduced. © 2013 Springer-Verlag.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.people | Connor R | it |
| dc.authority.people | Cardillo FA | it |
| dc.authority.people | Moss R | it |
| dc.authority.people | Rabitti F | it |
| dc.collection.id.s | 71c7200a-7c5f-4e83-8d57-d3d2ba88f40d | * |
| dc.collection.name | 04.01 Contributo in Atti di convegno | * |
| dc.contributor.appartenenza | Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" - ISTI | * |
| dc.contributor.appartenenza | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | * |
| dc.contributor.appartenenza.mi | 918 | * |
| dc.contributor.appartenenza.mi | 973 | * |
| dc.date.accessioned | 2024/02/21 03:29:26 | - |
| dc.date.available | 2024/02/21 03:29:26 | - |
| dc.date.issued | 2013 | - |
| dc.description.abstracteng | Jensen-Shannon divergence is a symmetrised, smoothed version of Küllback-Leibler. It has been shown to be the square of a proper distance metric, and has other properties which make it an excellent choice for many high-dimensional spaces in R*. The metric as defined is however expensive to evaluate. In sparse spaces over many dimensions the Intrinsic Dimensionality of the metric space is typically very high, making similarity-based indexing ineffectual. Exhaustive searching over large data collections may be infeasible. Using a property that allows the distance to be evaluated from only those dimensions which are non-zero in both arguments, and through the identification of a threshold function, we show that the cost of the function can be dramatically reduced. © 2013 Springer-Verlag. | - |
| dc.description.affiliations | Department of Computer and Information Sciences, University of Strathclyde, Glasgow, G1 1XH, , United Kingdom; ISTI (Information Science and Technology Institute), National Research Council of Italy, Via Moruzzi 1, 56124 Pisa, , , Italy; ISTI (Information Science and Technology Institute), National Research Council of Italy, Via Moruzzi 1, 56124 Pisa, , , Italy | - |
| dc.description.allpeople | Connor, R; Cardillo, Fa; Moss, R; Rabitti, F | - |
| dc.description.allpeopleoriginal | Connor R.; Cardillo F.A.; Moss R.; Rabitti F. | - |
| dc.description.fulltext | none | en |
| dc.description.numberofauthors | 4 | - |
| dc.identifier.doi | 10.1007/978-3-642-41062-8_16 | - |
| dc.identifier.isbn | 978-3-642-41061-1 | - |
| dc.identifier.isi | WOS:000338111900016 | - |
| dc.identifier.scopus | 2-s2.0-84886443337 | - |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/339508 | - |
| dc.identifier.url | http://www.scopus.com/record/display.url?eid=2-s2.0-84886443337&origin=inward | - |
| dc.language.iso | eng | - |
| dc.relation.alleditors | Nieves BrisaboaOscar PedreiraPavel Zezula | - |
| dc.relation.conferencedate | 2-4/10/2013 | - |
| dc.relation.conferencename | Similarity Search and Applications | - |
| dc.relation.firstpage | 163 | - |
| dc.relation.ispartofbook | Similarity Search and Applications | - |
| dc.relation.lastpage | 168 | - |
| dc.relation.volume | 8199 LNCS | - |
| dc.subject.keywords | similarity search | - |
| dc.subject.singlekeyword | similarity search | * |
| dc.title | Evaluation of Jensen-Shannon distance over sparse data | en |
| dc.type.driver | info:eu-repo/semantics/conferenceObject | - |
| dc.type.full | 04 Contributo in convegno::04.01 Contributo in Atti di convegno | it |
| dc.type.miur | 273 | - |
| dc.type.referee | Sì, ma tipo non specificato | - |
| dc.ugov.descaux1 | 382535 | - |
| iris.isi.extIssued | 2013 | - |
| iris.isi.extTitle | Evaluation of Jensen-Shannon Distance over Sparse Data | - |
| iris.isi.ideLinkStatusDate | 2026/03/04 12:35:21 | * |
| iris.isi.ideLinkStatusMillisecond | 1772624121592 | * |
| iris.orcid.lastModifiedDate | 2026/03/04 12:35:21 | * |
| iris.orcid.lastModifiedMillisecond | 1772624121583 | * |
| iris.scopus.extIssued | 2013 | - |
| iris.scopus.extTitle | Evaluation of Jensen-Shannon distance over sparse data | - |
| iris.sitodocente.maxattempts | 2 | - |
| iris.unpaywall.doi | 10.1007/978-3-642-41062-8_16 | * |
| iris.unpaywall.isoa | false | * |
| iris.unpaywall.journalisindoaj | false | * |
| iris.unpaywall.metadataCallLastModified | 05/03/2026 04:57:40 | - |
| iris.unpaywall.metadataCallLastModifiedMillisecond | 1772683060072 | - |
| iris.unpaywall.oastatus | closed | * |
| isi.authority.anceserie | LECTURE NOTES IN COMPUTER SCIENCE###0302-9743 | * |
| isi.category | EX | * |
| isi.category | ET | * |
| isi.contributor.affiliation | University of Strathclyde | - |
| isi.contributor.affiliation | Consiglio Nazionale delle Ricerche (CNR) | - |
| isi.contributor.affiliation | University of Strathclyde | - |
| isi.contributor.affiliation | Consiglio Nazionale delle Ricerche (CNR) | - |
| isi.contributor.country | Scotland | - |
| isi.contributor.country | Italy | - |
| isi.contributor.country | Scotland | - |
| isi.contributor.country | Italy | - |
| isi.contributor.name | Richard | - |
| isi.contributor.name | Franco Alberto | - |
| isi.contributor.name | Robert | - |
| isi.contributor.name | Fausto | - |
| isi.contributor.researcherId | DVM-3552-2022 | - |
| isi.contributor.researcherId | AAP-5764-2021 | - |
| isi.contributor.researcherId | DHQ-1155-2022 | - |
| isi.contributor.researcherId | DNK-4218-2022 | - |
| isi.contributor.subaffiliation | Dept Comp & Informat Sci | - |
| isi.contributor.subaffiliation | Natl Res Council Italy | - |
| isi.contributor.subaffiliation | Dept Comp & Informat Sci | - |
| isi.contributor.subaffiliation | Natl Res Council Italy | - |
| isi.contributor.surname | Connor | - |
| isi.contributor.surname | Cardillo | - |
| isi.contributor.surname | Moss | - |
| isi.contributor.surname | Rabitti | - |
| isi.date.issued | 2013 | * |
| isi.description.abstracteng | Jensen-Shannon divergence is a symmetrised, smoothed version of Kullback-Leibler. It has been shown to be the square of a proper distance metric, and has other properties which make it an excellent choice for many high-dimensional spaces in R*.The metric as defined is however expensive to evaluate. In sparse spaces over many dimensions the Intrinsic Dimensionality of the metric space is typically very high, making similarity-based indexing ineffectual. Exhaustive searching over large data collections may be infeasible.Using a property that allows the distance to be evaluated from only those dimensions which are non-zero in both arguments, and through the identification of a threshold function, we show that the cost of the function can be dramatically reduced. | * |
| isi.description.allpeopleoriginal | Connor, R; Cardillo, FA; Moss, R; Rabitti, F; | * |
| isi.document.sourcetype | WOS.ISTP | * |
| isi.document.type | Proceedings Paper | * |
| isi.document.types | Proceedings Paper | * |
| isi.identifier.isi | WOS:000338111900016 | * |
| isi.journal.journaltitle | SIMILARITY SEARCH AND APPLICATIONS (SISAP) | * |
| isi.journal.journaltitleabbrev | LECT NOTES COMPUT SC | * |
| isi.language.original | English | * |
| isi.publisher.place | HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY | * |
| isi.relation.firstpage | 163 | * |
| isi.relation.lastpage | 168 | * |
| isi.relation.volume | 8199 | * |
| isi.title | Evaluation of Jensen-Shannon Distance over Sparse Data | * |
| scopus.authority.anceserie | LECTURE NOTES IN COMPUTER SCIENCE###0302-9743 | * |
| scopus.category | 2614 | * |
| scopus.category | 1700 | * |
| scopus.contributor.affiliation | University of Strathclyde | - |
| scopus.contributor.affiliation | National Research Council of Italy | - |
| scopus.contributor.affiliation | University of Strathclyde | - |
| scopus.contributor.affiliation | National Research Council of Italy | - |
| scopus.contributor.afid | 60024724 | - |
| scopus.contributor.afid | 60085207 | - |
| scopus.contributor.afid | 60024724 | - |
| scopus.contributor.afid | 60085207 | - |
| scopus.contributor.auid | 7102097432 | - |
| scopus.contributor.auid | 57191090133 | - |
| scopus.contributor.auid | 57197373410 | - |
| scopus.contributor.auid | 6602132101 | - |
| scopus.contributor.country | United Kingdom | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | United Kingdom | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.dptid | 113500075 | - |
| scopus.contributor.dptid | - | |
| scopus.contributor.dptid | 113500075 | - |
| scopus.contributor.dptid | - | |
| scopus.contributor.name | Richard | - |
| scopus.contributor.name | Franco Alberto | - |
| scopus.contributor.name | Robert | - |
| scopus.contributor.name | Fausto | - |
| scopus.contributor.subaffiliation | Department of Computer and Information Sciences; | - |
| scopus.contributor.subaffiliation | ISTI (Information Science and Technology Institute); | - |
| scopus.contributor.subaffiliation | Department of Computer and Information Sciences; | - |
| scopus.contributor.subaffiliation | ISTI (Information Science and Technology Institute); | - |
| scopus.contributor.surname | Connor | - |
| scopus.contributor.surname | Cardillo | - |
| scopus.contributor.surname | Moss | - |
| scopus.contributor.surname | Rabitti | - |
| scopus.date.issued | 2013 | * |
| scopus.description.abstracteng | Jensen-Shannon divergence is a symmetrised, smoothed version of Küllback-Leibler. It has been shown to be the square of a proper distance metric, and has other properties which make it an excellent choice for many high-dimensional spaces in ℝ*. The metric as defined is however expensive to evaluate. In sparse spaces over many dimensions the Intrinsic Dimensionality of the metric space is typically very high, making similarity-based indexing ineffectual. Exhaustive searching over large data collections may be infeasible. Using a property that allows the distance to be evaluated from only those dimensions which are non-zero in both arguments, and through the identification of a threshold function, we show that the cost of the function can be dramatically reduced. © 2013 Springer-Verlag. | * |
| scopus.description.allpeopleoriginal | Connor R.; Cardillo F.A.; Moss R.; Rabitti F. | * |
| scopus.differences | scopus.authority.anceserie | * |
| scopus.differences | scopus.relation.conferencedate | * |
| scopus.differences | scopus.description.abstracteng | * |
| scopus.differences | scopus.relation.conferencename | * |
| scopus.differences | scopus.identifier.isbn | * |
| scopus.differences | scopus.relation.conferenceplace | * |
| scopus.differences | scopus.relation.volume | * |
| scopus.document.type | cp | * |
| scopus.document.types | cp | * |
| scopus.identifier.doi | 10.1007/978-3-642-41062-8_16 | * |
| scopus.identifier.eissn | 1611-3349 | * |
| scopus.identifier.isbn | 9783642410611 | * |
| scopus.identifier.pui | 370112784 | * |
| scopus.identifier.scopus | 2-s2.0-84886443337 | * |
| scopus.journal.sourceid | 25674 | * |
| scopus.language.iso | eng | * |
| scopus.relation.conferencedate | 2013 | * |
| scopus.relation.conferencename | 6th International Conference on Similarity Search and Applications, SISAP 2013 | * |
| scopus.relation.conferenceplace | A Coruna, esp | * |
| scopus.relation.firstpage | 163 | * |
| scopus.relation.lastpage | 168 | * |
| scopus.relation.volume | 8199 | * |
| scopus.title | Evaluation of Jensen-Shannon distance over sparse data | * |
| scopus.titleeng | Evaluation of Jensen-Shannon distance over sparse data | * |
| Appare nelle tipologie: | 04.01 Contributo in Atti di convegno | |
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
