<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-03116610</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-15T21:51:33+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Selectivity Estimation with Attribute Value Dependencies Using Linked Bayesian Networks</title>
            <author role="aut">
              <persName>
                <forename type="first">Max</forename>
                <surname>Halford</surname>
              </persName>
              <email type="md5">fb7646848ce98ca4e0813dd1b8dc9a1c</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">max-halford</idno>
              <idno type="idhal" notation="numeric">735171</idno>
              <idno type="halauthorid" notation="string">48717-735171</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=erRNNi0AAAAJ&amp;hl=en</idno>
              <orgName ref="#struct-217752"/>
              <affiliation ref="#struct-1954"/>
              <affiliation ref="#struct-1001829"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Philippe</forename>
                <surname>Saint-Pierre</surname>
              </persName>
              <email type="md5">e793d2dcd2f04495c1f59a9454704bb6</email>
              <email type="domain">math.univ-toulouse.fr</email>
              <idno type="idhal" notation="string">philippe-saint-pierre</idno>
              <idno type="idhal" notation="numeric">1255590</idno>
              <idno type="halauthorid" notation="string">732576-1255590</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7367-3770</idno>
              <idno type="IDREF">https://www.idref.fr/088404196</idno>
              <affiliation ref="#struct-1954"/>
              <affiliation ref="#struct-301366"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Franck</forename>
                <surname>Morvan</surname>
              </persName>
              <email type="md5">b0c969b74778cfca32c711ead7b8af00</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">franck-morvan</idno>
              <idno type="idhal" notation="numeric">743127</idno>
              <idno type="halauthorid" notation="string">21206-743127</idno>
              <idno type="IDREF">https://www.idref.fr/034867406</idno>
              <idno type="VIAF">https://viaf.org/viaf/132793219</idno>
              <affiliation ref="#struct-1001829"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Franck</forename>
                <surname>Morvan</surname>
              </persName>
              <email type="md5">b0c969b74778cfca32c711ead7b8af00</email>
              <email type="domain">irit.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-01-20 14:29:08</date>
              <date type="whenModified">2025-10-22 18:04:08</date>
              <date type="whenReleased">2021-01-20 14:29:08</date>
              <date type="whenProduced">2020-11-20</date>
              <ref type="externalLink" target="http://arxiv.org/pdf/2009.09883"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="430353">
                <persName>
                  <forename>Franck</forename>
                  <surname>Morvan</surname>
                </persName>
                <email type="md5">b0c969b74778cfca32c711ead7b8af00</email>
                <email type="domain">irit.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03116610</idno>
            <idno type="halUri">https://hal.science/hal-03116610</idno>
            <idno type="halBibtex">halford:hal-03116610</idno>
            <idno type="halRefHtml">&lt;i&gt;Lecture Notes in Computer Science&lt;/i&gt;, 2020, Transactions on Large-Scale Data- and Knowledge-Centered Systems XLVI, 12410, pp.154-188. &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-662-62386-2_6"&gt;&amp;#x27E8;10.1007/978-3-662-62386-2_6&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Lecture Notes in Computer Science, 2020, Transactions on Large-Scale Data- and Knowledge-Centered Systems XLVI, 12410, pp.154-188. &amp;#x27E8;10.1007/978-3-662-62386-2_6&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLSE2">Université Toulouse 2</idno>
            <idno type="stamp" n="UNIV-TLSE3">Université de Toulouse</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INSA-TOULOUSE">Institut National des Sciences Appliquées de Toulouse</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="IMT">Institut de Mathématiques de Toulouse</idno>
            <idno type="stamp" n="UT1-CAPITOLE">Université Toulouse 1 Capitole</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="IRIT">IRIT - Institut de Recherche en Informatique de Toulouse</idno>
            <idno type="stamp" n="IRIT-PYRAMIDE" corresp="IRIT">Optimisation Dynamique de Requêtes Réparties à grande échelle</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="IRIT-GD" corresp="IRIT">Gestion des Données</idno>
            <idno type="stamp" n="IRIT-UT3">IRIT - Université Toulouse III Paul Sabatier</idno>
            <idno type="stamp" n="TOULOUSE-INP">Toulouse - INP</idno>
            <idno type="stamp" n="UNIV-UT3">Université Toulouse 3</idno>
            <idno type="stamp" n="UT3-INP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="UT3-TOULOUSEINP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="IUT_UT3">IUT Paul Sabatier</idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">ISBN 978-3-662-62385-5</note>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Selectivity Estimation with Attribute Value Dependencies Using Linked Bayesian Networks</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Max</forename>
                    <surname>Halford</surname>
                  </persName>
                  <email type="md5">fb7646848ce98ca4e0813dd1b8dc9a1c</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">max-halford</idno>
                  <idno type="idhal" notation="numeric">735171</idno>
                  <idno type="halauthorid" notation="string">48717-735171</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=erRNNi0AAAAJ&amp;hl=en</idno>
                  <orgName ref="#struct-217752"/>
                  <affiliation ref="#struct-1954"/>
                  <affiliation ref="#struct-1001829"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Philippe</forename>
                    <surname>Saint-Pierre</surname>
                  </persName>
                  <email type="md5">e793d2dcd2f04495c1f59a9454704bb6</email>
                  <email type="domain">math.univ-toulouse.fr</email>
                  <idno type="idhal" notation="string">philippe-saint-pierre</idno>
                  <idno type="idhal" notation="numeric">1255590</idno>
                  <idno type="halauthorid" notation="string">732576-1255590</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7367-3770</idno>
                  <idno type="IDREF">https://www.idref.fr/088404196</idno>
                  <affiliation ref="#struct-1954"/>
                  <affiliation ref="#struct-301366"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Franck</forename>
                    <surname>Morvan</surname>
                  </persName>
                  <email type="md5">b0c969b74778cfca32c711ead7b8af00</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">franck-morvan</idno>
                  <idno type="idhal" notation="numeric">743127</idno>
                  <idno type="halauthorid" notation="string">21206-743127</idno>
                  <idno type="IDREF">https://www.idref.fr/034867406</idno>
                  <idno type="VIAF">https://viaf.org/viaf/132793219</idno>
                  <affiliation ref="#struct-1001829"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">47704</idno>
                <idno type="issn">0302-9743</idno>
                <title level="j">Lecture Notes in Computer Science</title>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="serie">Transactions on Large-Scale Data- and Knowledge-Centered Systems XLVI</biblScope>
                  <biblScope unit="volume">12410</biblScope>
                  <biblScope unit="pp">154-188</biblScope>
                  <date type="datePub">2020-11-20</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-662-62386-2_6</idno>
              <ref type="publisher">https://link.springer.com/chapter/10.1007%2F978-3-662-62386-2_6</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Query optimisation</term>
                <term xml:lang="en">Cost model</term>
                <term xml:lang="en">Selectivity estimation</term>
                <term xml:lang="en">Bayesian networks</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-db">Computer Science [cs]/Databases [cs.DB]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Relational query optimisers rely on cost models to choose between different query execution plans. Selectivity estimates are known to be a crucial input to the cost model. In practice, standard selectivity estimation procedures are prone to large errors. This is mostly because they rely on the so-called attribute value independence and join uniformity assumptions. Therefore, multidimensional methods have been proposed to capture dependencies between two or more attributes both within and across relations. However, these methods require a large computational cost which makes them unusable in practice. We propose a method based on Bayesian networks that is able to capture cross-relation attribute value dependencies with little overhead. Our proposal is based on the assumption that dependencies between attributes are preserved when joins are involved. Furthermore, we introduce a parameter for trading between estimation accuracy and computational cost. We validate our work by comparing it with other relevant methods on a large workload derived from the JOB and TPC-DS benchmarks. Our results show that our method is an order of magnitude more efficient than existing methods, whilst maintaining a high level of accuracy.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1954" status="OLD">
          <idno type="IdRef">166783900</idno>
          <idno type="ISNI">0000000403836348</idno>
          <idno type="RNSR">200711888W</idno>
          <idno type="ROR">https://ror.org/014vp6c30</idno>
          <orgName>Institut de Mathématiques de Toulouse UMR5219</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2007-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>UPS IMT, F-31062 Toulouse Cedex 9, INSA Toulouse, F-31077 Toulouse,France UT1, F-31042 Toulouse, France UT2, F-31058 Toulouse,Téléphone : 05.61.55.67.90</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.math.univ-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116255" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-217752" type="direct"/>
            <relation name="UMR5219" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1001829" status="OLD">
          <orgName>Optimisation Dynamique de Requêtes Réparties à grande échelle</orgName>
          <orgName type="acronym">IRIT-PYRAMIDE</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Institut de recherche en informatique de Toulouse - IRIT118 Route de Narbonne 31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irit.fr/departement/gestion-des-donnees/equipe-pyramide/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-34499" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-217752" type="indirect"/>
            <relation name="UMR5505 / URA1399" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
            <relation active="#struct-1149079" type="indirect"/>
            <relation name="FED4171" active="#struct-217752" type="indirect"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-301366" status="OLD">
          <orgName>Institut Universitaire de Technologie - Paul Sabatier</orgName>
          <orgName type="acronym">IUT Toulouse Auch Castres</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Université Toulouse III - 115C, route de Narbonne - 31077 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://iut.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-217752" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81148" status="VALID">
          <idno type="IdRef">026404354</idno>
          <idno type="ISNI">0000000121902837</idno>
          <idno type="ROR">https://ror.org/0443n9e75</idno>
          <orgName>Université Toulouse Capitole</orgName>
          <orgName type="acronym">UT Capitole</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>2 rue du Doyen-Gabriel-Marty - 31042 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ut-capitole.fr/</ref>
          </desc>
          <listRelation>
            <relation name="443875" active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-443875" status="VALID">
          <idno type="ROR">https://ror.org/017tgbk05</idno>
          <orgName>Communauté d'universités et établissements de Toulouse</orgName>
          <orgName type="acronym">Comue de Toulouse</orgName>
          <desc>
            <address>
              <addrLine>41 Allée Jules Guesde, 31000 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-toulouse.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116255" status="VALID">
          <idno type="IdRef">026388766</idno>
          <idno type="ISNI">0000 0001 2286 8343</idno>
          <idno type="ROR">https://ror.org/01h8pf755</idno>
          <idno type="Wikidata">Q858979</idno>
          <orgName>Institut National des Sciences Appliquées - Toulouse</orgName>
          <orgName type="acronym">INSA Toulouse</orgName>
          <date type="start">1963-10-21</date>
          <desc>
            <address>
              <addrLine>135, avenue de Rangueil - 31077 Toulouse cedex 4</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-toulouse.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" type="direct"/>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116256" status="VALID">
          <idno type="IdRef">026403994</idno>
          <idno type="ROR">https://ror.org/04ezk3x31</idno>
          <orgName>Université Toulouse - Jean Jaurès</orgName>
          <orgName type="acronym">UT2J</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <addrLine>5 allées Antonio Machado - 31058 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse2.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-217752" status="OLD">
          <idno type="IdRef">026404672</idno>
          <idno type="ISNI">0000000121617331</idno>
          <idno type="ROR">https://ror.org/02v6kpv12</idno>
          <idno type="Wikidata">Q1273188</idno>
          <orgName>Université Toulouse III - Paul Sabatier</orgName>
          <orgName type="acronym">UT3</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 route de Narbonne - 31062 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-34499" status="OLD">
          <idno type="IdRef">030947448</idno>
          <idno type="ISNI">0000000121927225</idno>
          <idno type="RNSR">199511949P</idno>
          <idno type="ROR">https://ror.org/01rx4qw44</idno>
          <orgName>Institut de recherche en informatique de Toulouse</orgName>
          <orgName type="acronym">IRIT</orgName>
          <date type="start">1990-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 Route de Narbonne, F-31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irit.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-217752" type="direct"/>
            <relation name="UMR5505 / URA1399" active="#struct-441569" type="direct"/>
            <relation active="#struct-448187" type="direct"/>
            <relation active="#struct-1149079" type="direct"/>
            <relation name="FED4171" active="#struct-217752" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-448187" status="VALID">
          <idno type="IdRef">026388820</idno>
          <idno type="ISNI">0000000121766169</idno>
          <idno type="ROR">https://ror.org/033p9g875</idno>
          <orgName>Institut National Polytechnique (Toulouse)</orgName>
          <orgName type="acronym">Toulouse INP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inp-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1149079" status="OLD">
          <orgName>Toulouse Mind &amp; Brain Institut</orgName>
          <orgName type="acronym">TMBI</orgName>
          <date type="start">2021-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>CHU Purpan, Pavillon Baudot, 31059 Toulouse cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.tmbi.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="FED4171" active="#struct-217752" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>