<?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-02053700</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="2026-05-03T11:00:15+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">SHCoClust, a Scalable Similarity-based Hierarchical Co-clustering Method and its Application to Textual Collections</title>
            <author role="aut">
              <persName>
                <forename type="first">Xinyu</forename>
                <surname>Wang</surname>
              </persName>
              <email type="md5">60195875ae2cae99cdad3d67583d9098</email>
              <email type="domain">univ-lyon2.fr</email>
              <idno type="idhal" notation="numeric">1006004</idno>
              <idno type="halauthorid" notation="string">720297-1006004</idno>
              <affiliation ref="#struct-183072"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Ah-Pine</surname>
              </persName>
              <email type="md5">15f627b00de0e26c5bd9269fa8190522</email>
              <email type="domain">univ-lyon2.fr</email>
              <idno type="idhal" notation="string">julien-ah-pine</idno>
              <idno type="idhal" notation="numeric">15506</idno>
              <idno type="halauthorid" notation="string">29462-15506</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6898-3961</idno>
              <affiliation ref="#struct-183072"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jérôme</forename>
                <surname>Darmont</surname>
              </persName>
              <email type="md5">f57379f23c3528d914f5810bff4939bc</email>
              <email type="domain">univ-lyon2.fr</email>
              <idno type="idhal" notation="string">jerome-darmont</idno>
              <idno type="idhal" notation="numeric">14011</idno>
              <idno type="halauthorid" notation="string">14423-14011</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1491-384X</idno>
              <idno type="IDREF">https://www.idref.fr/081304668</idno>
              <idno type="ARXIV">https://arxiv.org/a/darmont_j_1</idno>
              <affiliation ref="#struct-183072"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Fabien</forename>
                <surname>Rico</surname>
              </persName>
              <email type="md5">3ea37c467df15b174043632df96f3c43</email>
              <email type="domain">univ-lyon1.fr</email>
            </editor>
            <funder>French national project PIA REQUEST</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2019-03-01 15:48:33</date>
              <date type="whenWritten">2017-02</date>
              <date type="whenModified">2025-09-03 09:56:15</date>
              <date type="whenReleased">2019-03-08 09:40:57</date>
              <date type="whenProduced">2017-07-09</date>
              <date type="whenEndEmbargoed">2019-03-01</date>
              <ref type="file" target="https://hal.science/hal-02053700v1/document">
                <date notBefore="2019-03-01"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02053700v1/file/PID4830385.pdf" id="file-2053911-2059220">
                <date notBefore="2019-03-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="104266">
                <persName>
                  <forename>Fabien</forename>
                  <surname>Rico</surname>
                </persName>
                <email type="md5">3ea37c467df15b174043632df96f3c43</email>
                <email type="domain">univ-lyon1.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02053700</idno>
            <idno type="halUri">https://hal.science/hal-02053700</idno>
            <idno type="halBibtex">wang:hal-02053700</idno>
            <idno type="halRefHtml">&lt;i&gt;2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)&lt;/i&gt;, Jul 2017, Naples, Italy. pp.F-0529</idno>
            <idno type="halRef">2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Jul 2017, Naples, Italy. pp.F-0529</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-2053911-2059220"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="ERIC" corresp="UNIV-LYON2">Equipe de Recherche en Ingénierie des Connaissances</idno>
            <idno type="stamp" n="LYON2">Université Lyon2</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">This paper is accepted as a long paper with an oral presentation by the IEEE international conference on fuzzy systems (FUZZ-IEEE 2017)</note>
            <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">SHCoClust, a Scalable Similarity-based Hierarchical Co-clustering Method and its Application to Textual Collections</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Xinyu</forename>
                    <surname>Wang</surname>
                  </persName>
                  <email type="md5">60195875ae2cae99cdad3d67583d9098</email>
                  <email type="domain">univ-lyon2.fr</email>
                  <idno type="idhal" notation="numeric">1006004</idno>
                  <idno type="halauthorid" notation="string">720297-1006004</idno>
                  <affiliation ref="#struct-183072"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Ah-Pine</surname>
                  </persName>
                  <email type="md5">15f627b00de0e26c5bd9269fa8190522</email>
                  <email type="domain">univ-lyon2.fr</email>
                  <idno type="idhal" notation="string">julien-ah-pine</idno>
                  <idno type="idhal" notation="numeric">15506</idno>
                  <idno type="halauthorid" notation="string">29462-15506</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6898-3961</idno>
                  <affiliation ref="#struct-183072"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jérôme</forename>
                    <surname>Darmont</surname>
                  </persName>
                  <email type="md5">f57379f23c3528d914f5810bff4939bc</email>
                  <email type="domain">univ-lyon2.fr</email>
                  <idno type="idhal" notation="string">jerome-darmont</idno>
                  <idno type="idhal" notation="numeric">14011</idno>
                  <idno type="halauthorid" notation="string">14423-14011</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1491-384X</idno>
                  <idno type="IDREF">https://www.idref.fr/081304668</idno>
                  <idno type="ARXIV">https://arxiv.org/a/darmont_j_1</idno>
                  <affiliation ref="#struct-183072"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)</title>
                <meeting>
                  <title>2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)</title>
                  <date type="start">2017-07-09</date>
                  <date type="end">2017-07-12</date>
                  <settlement>Naples</settlement>
                  <country key="IT">Italy</country>
                </meeting>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="pp">F-0529</biblScope>
                  <date type="datePub">2017-07</date>
                </imprint>
              </monogr>
              <ref type="publisher">http://www.fuzzieee2017.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">text clustering</term>
                <term xml:lang="en">bipartite spectral co-clustering</term>
                <term xml:lang="en">similarity-based agglomerative hierarchical clustering</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</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>In comparison with flat clustering methods, such as K-means, hierarchical clustering and co-clustering methods are more advantageous, for the reason that hierarchical clustering is capable to reveal the internal connections of clusters, and co-clustering can yield clusters of data instances and features. Interested in organizing co-clusters in hierarchies and in discovering cluster hierarchies inside co-clusters, in this paper, we propose SHCoClust, a scalable similarity-based hierarchical co-clustering method. Except possessing the above-mentioned advantages in unison, SHCoClust is able to employ kernel functions, thanks to its utilization of inner product. Furthermore, having all similarities between 0 and 1, the input of SHCoClust can be sparsified by threshold values, so that less memory and less time are required for storage and for computation. This grants SHCoClust scalability, i.e, the ability to process relatively large datasets with reduced and limited computing resources. Our experiments demonstrate that SHCoClust significantly out-performs the conventional hierarchical clustering methods. In addition, with sparsifying the input similarity matrices obtained by linear kernel and by Gaussian kernel, SHCoClust is capable to guarantee the clustering quality, even when its input being largely sparsified. Consequently, up to 86% time gain and on average 75% memory gain are achieved.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-183072" status="VALID">
          <idno type="IdRef">168642174</idno>
          <idno type="RNSR">199914397H</idno>
          <idno type="ROR">https://ror.org/009frb846</idno>
          <orgName>Entrepôts, Représentation et Ingénierie des Connaissances</orgName>
          <orgName type="acronym">ERIC</orgName>
          <desc>
            <address>
              <addrLine>Université Lumière Lyon 2 5 avenue Pierre Mendès-France 69676 Bron Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://eric.univ-lyon2.fr</ref>
          </desc>
          <listRelation>
            <relation name="EA3083" active="#struct-33804" type="direct"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>