<?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-02880553</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="2026-05-14T20:51:14+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Discovering Approximate Functional Dependencies using Smoothed Mutual Information</title>
            <author role="aut">
              <persName>
                <forename type="first">Frédéric</forename>
                <surname>Pennerath</surname>
              </persName>
              <email type="md5">d019239a535728da78ba11aaee064e15</email>
              <email type="domain">centralesupelec.fr</email>
              <idno type="idhal" notation="string">frederic-pennerath</idno>
              <idno type="idhal" notation="numeric">7783</idno>
              <idno type="halauthorid" notation="string">6697-7783</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2202-5896</idno>
              <idno type="IDREF">https://www.idref.fr/137563957</idno>
              <affiliation ref="#struct-205125"/>
              <affiliation ref="#struct-411575"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Panagiotis</forename>
                <surname>Mandros</surname>
              </persName>
              <idno type="halauthorid">1990173-0</idno>
              <affiliation ref="#struct-234715"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jilles</forename>
                <surname>Vreeken</surname>
              </persName>
              <idno type="halauthorid">1990174-0</idno>
              <affiliation ref="#struct-573058"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Frédéric</forename>
                <surname>Pennerath</surname>
              </persName>
              <email type="md5">d019239a535728da78ba11aaee064e15</email>
              <email type="domain">centralesupelec.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-06-25 09:49:43</date>
              <date type="whenModified">2025-11-04 11:59:33</date>
              <date type="whenReleased">2020-07-01 15:47:35</date>
              <date type="whenProduced">2020-08-22</date>
              <date type="whenEndEmbargoed">2020-06-25</date>
              <ref type="file" target="https://centralesupelec.hal.science/hal-02880553v1/document">
                <date notBefore="2020-06-25"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://centralesupelec.hal.science/hal-02880553v1/file/smoothed-info-article-without-ACM.pdf" id="file-2880553-2532898">
                <date notBefore="2020-06-25"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="107297">
                <persName>
                  <forename>Frédéric</forename>
                  <surname>Pennerath</surname>
                </persName>
                <email type="md5">d019239a535728da78ba11aaee064e15</email>
                <email type="domain">centralesupelec.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02880553</idno>
            <idno type="halUri">https://centralesupelec.hal.science/hal-02880553</idno>
            <idno type="halBibtex">pennerath:hal-02880553</idno>
            <idno type="halRefHtml">&lt;i&gt;KDD 2020 - 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining&lt;/i&gt;, Aug 2020, San Diego / Virtual, United States. pp.1254 -- 1264</idno>
            <idno type="halRef">KDD 2020 - 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aug 2020, San Diego / Virtual, United States. pp.1254 -- 1264</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2880553-2532898"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="INRIA-NANCY-GRAND-EST">INRIA Nancy - Grand Est</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-NLPKD" corresp="LORIA">Department of Natural Language Processing &amp; Knowledge Discovery</idno>
            <idno type="stamp" n="HUB-IA">Hub Intelligence Artificielle de CentraleSupélec</idno>
            <idno type="stamp" n="INRIA-ALLEMAGNE">INRIA-ALLEMAGNE</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Discovering Approximate Functional Dependencies using Smoothed Mutual Information</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Frédéric</forename>
                    <surname>Pennerath</surname>
                  </persName>
                  <email type="md5">d019239a535728da78ba11aaee064e15</email>
                  <email type="domain">centralesupelec.fr</email>
                  <idno type="idhal" notation="string">frederic-pennerath</idno>
                  <idno type="idhal" notation="numeric">7783</idno>
                  <idno type="halauthorid" notation="string">6697-7783</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2202-5896</idno>
                  <idno type="IDREF">https://www.idref.fr/137563957</idno>
                  <affiliation ref="#struct-205125"/>
                  <affiliation ref="#struct-411575"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Panagiotis</forename>
                    <surname>Mandros</surname>
                  </persName>
                  <idno type="halauthorid">1990173-0</idno>
                  <affiliation ref="#struct-234715"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jilles</forename>
                    <surname>Vreeken</surname>
                  </persName>
                  <idno type="halauthorid">1990174-0</idno>
                  <affiliation ref="#struct-573058"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>KDD 2020 - 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining</title>
                  <date type="start">2020-08-22</date>
                  <date type="end">2020-08-27</date>
                  <settlement>San Diego / Virtual</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <publisher>ACM</publisher>
                  <biblScope unit="serie">KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &amp; Data Mining</biblScope>
                  <biblScope unit="pp">1254 -- 1264</biblScope>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Laplace smoothing</term>
                <term xml:lang="en">functional dependencies</term>
                <term xml:lang="en">mutual information</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>We consider the task of discovering the top-K reliable approximate functional dependencies X → Y from high dimensional data. While naively maximizing mutual information involving high dimensional entropies over empirical data is subject to false discoveries, correcting the empirical estimator against data sparsity can lead to efficient exact algorithms for robust dependency discovery. Previous approaches focused on correcting by subtracting expected values of different null hypothesis models. In this paper, we consider a different correction strategy and counter data sparsity using uniform priors and smoothing techniques, that leads to an efficient and robust estimating process. In addition, we derive an admissible and tight bounding function for the smoothed estimator that allows us to efficiently solve via branch-and-bound the hard search problem for the top-K dependencies. Our experiments show that our approach is much faster than previous proposals, and leads to the discovery of sparse and informative functional dependencies. CCS CONCEPTS • Information systems → Data mining.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-205125" status="OLD">
          <idno type="RNSR">200818291B</idno>
          <orgName>Knowledge  representation, reasonning</orgName>
          <orgName type="acronym">ORPAILLEUR</orgName>
          <date type="start">2008-01-01</date>
          <date type="end">2020-06-30</date>
          <desc>
            <address>
              <addrLine>Centre Inria de l'Université de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/orpailleur</ref>
          </desc>
          <listRelation>
            <relation active="#struct-129671" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-423086" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-234715" status="VALID">
          <idno type="ROR">https://ror.org/01w19ak89</idno>
          <orgName>Max Planck Institute for Informatics [Saarbrücken]</orgName>
          <desc>
            <address>
              <addrLine>Campus 4, 66123 Saarbrücken</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.mpi-inf.mpg.de/home/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-573058" status="VALID">
          <idno type="ROR">https://ror.org/02njgxr09</idno>
          <orgName>Helmholtz Center for Information Security [Saarbrücken]</orgName>
          <orgName type="acronym">CISPA</orgName>
          <desc>
            <address>
              <addrLine>Stuhlsatzenhaus 566123 Saarbrücken</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://cispa.saarland/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-129671" status="VALID">
          <idno type="RNSR">198618246Y</idno>
          <idno type="ROR">https://ror.org/03fcjvn64</idno>
          <orgName>Centre Inria de l'Université de Lorraine</orgName>
          <desc>
            <address>
              <addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/nancy</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="department" xml:id="struct-423086" status="VALID">
          <orgName>Department of Natural Language Processing &amp; Knowledge Discovery</orgName>
          <orgName type="acronym">LORIA - NLPKD</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/natural-language-processing-and-knowledge-discovery/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.fr/</ref>
          </desc>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>