Show simple item record

dc.contributor.authorGünther, Michael
dc.contributor.authorThiele, Maik
dc.contributor.authorLehner, Wolfgang
dc.contributor.editorGrust, Torsten
dc.contributor.editorNaumann, Felix
dc.contributor.editorBöhm, Alexander
dc.contributor.editorLehner, Wolfgang
dc.contributor.editorHärder, Theo
dc.contributor.editorRahm, Erhard
dc.contributor.editorHeuer, Andreas
dc.contributor.editorKlettke, Meike
dc.contributor.editorMeyer, Holger
dc.date.accessioned2019-04-11T07:21:17Z
dc.date.available2019-04-11T07:21:17Z
dc.date.issued2019
dc.identifier.isbn978-3-88579-683-1
dc.identifier.issn1617-5468
dc.identifier.urihttp://dl.gi.de/handle/20.500.12116/21699
dc.description.abstractK nearest neighbor search (kNN-Search) is a universal data processing technique and a fundamental operation for word embeddings trained by word2vec or related approaches. The benefits of operations on dense vectors like word embeddings for analytical functionalities of RDBMSs motivate an integration of kNN-Joins. However, kNN-Search, as well as kNN-Joins, have barely been integrated into relational database systems so far. In this paper, we develop an index structure for approximated kNN-Joins working well on high-dimensional data and provide an integration into PostgreSQL. The novel index structure is efficient for different cardinalities of the involved join partners. An evaluation of the system based on applications on word embeddings shows the benefits of such an integrated kNN-Join operation and the performance of the proposed approach.en
dc.language.isoen
dc.publisherGesellschaft für Informatik, Bonn
dc.relation.ispartofBTW 2019
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) – Proceedings, Volume P-289
dc.subjectapproximated nearest neighbor search
dc.subjectproduct quantization
dc.subjectRDBMS
dc.subjectword embeddings
dc.titleFast Approximated Nearest Neighbor Joins For Relational Database Systemsen
mci.reference.pages225-244
mci.conference.sessiontitleWissenschaftliche Beiträge
mci.conference.locationRostock
mci.conference.date4.-8. März 2019
dc.identifier.doi10.18420/btw2019-15


Files in this item

Thumbnail

Show simple item record