Publication:
Optimizing Learned Bloom Filters: How Much Should Be Learned?

dc.affiliation.dptoUC3M. Departamento de Ingeniería Telemáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Network Technologieses
dc.contributor.authorDai, Zhenwei
dc.contributor.authorShrivastava, Ansumali
dc.contributor.authorReviriego Vasallo, Pedro
dc.contributor.authorHernández Gutiérrez, José Alberto
dc.contributor.funderEuropean Commissionen
dc.date.accessioned2022-09-30T10:35:59Z
dc.date.available2022-09-30T10:35:59Z
dc.date.issued2022-03-03
dc.description.abstractThe learned Bloom filter (LBF) combines a machine learning model (learner) with a traditional Bloom filter to improve the false positive rate (FPR) that can be achieved for a given memory budget. The LBF has recently been generalized by making use of the full spectrum of the learner's prediction score. However, in all those designs, the machine learning model is fixed. In this letter, for the first time, the design of LBFs is proposed and evaluated by considering the machine learning model as one of the variables in the process. In detail, for a given memory budget, several LBFs are constructed using different machine learning models and the one with the lowest FPR is selected. We demonstrate that our approach can achieve much better performance than existing LBF designs providing reductions of the FPR of up to 90% in some settings.en
dc.description.sponsorshipThis work was supported by the EU H2020 Project PIMCITY under Grant H2020-871370. This manuscript was recommended for publication by A. Kumar.en
dc.format.extent4
dc.identifier.bibliographicCitationDai, Z., Shrivastava, A., Reviriego, P. & Hernandez, J. A. (2022, septiembre). Optimizing Learned Bloom Filters: How Much Should Be Learned? IEEE Embedded Systems Letters, 14(3), 123-126.en
dc.identifier.doihttps://doi.org/10.1109/LES.2022.3156019
dc.identifier.issn1943-0663
dc.identifier.publicationfirstpage123
dc.identifier.publicationissue3
dc.identifier.publicationlastpage126
dc.identifier.publicationtitleIEEE Embedded Systems Lettersen
dc.identifier.publicationvolume14
dc.identifier.urihttps://hdl.handle.net/10016/35826
dc.identifier.uxxiAR/0000030309
dc.language.isoeng
dc.publisherIEEEen
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/871370en
dc.rights© 2022 IEEE.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaIngeniería Mecánicaes
dc.subject.otherLearned bloom filters (lbfs)en
dc.subject.otherMachine learningen
dc.subject.otherNetworkingen
dc.subject.otherUrl classificationen
dc.titleOptimizing Learned Bloom Filters: How Much Should Be Learned?en
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Optimizing_IEEEESL_2022_ps.pdf
Size:
1.09 MB
Format:
Adobe Portable Document Format