<?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-02277646</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="2026-05-24T05:57:04+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Stochastic Graphlet Embedding</title>
            <author role="aut">
              <persName>
                <forename type="first">Anjan</forename>
                <surname>Dutta</surname>
              </persName>
              <idno type="halauthorid">732255-0</idno>
              <affiliation ref="#struct-19095"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hichem</forename>
                <surname>Sahbi</surname>
              </persName>
              <email type="md5">bd06ee81c3ee1dee3fcba8b296500031</email>
              <email type="domain">lip6.fr</email>
              <idno type="idhal" notation="string">hichem-sahbi</idno>
              <idno type="idhal" notation="numeric">742003</idno>
              <idno type="halauthorid" notation="string">52390-742003</idno>
              <idno type="IDREF">https://www.idref.fr/077125223</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6813-9146</idno>
              <affiliation ref="#struct-541720"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gestionnaire HAL 3</forename>
                <surname>Sorbonne Université</surname>
              </persName>
              <email type="md5">a829e169d53d985531a4db19c33011d6</email>
              <email type="domain">sorbonne-universite.fr</email>
            </editor>
            <funder ref="#projanr-33739"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2019-09-03 17:32:43</date>
              <date type="whenModified">2024-10-30 19:43:10</date>
              <date type="whenReleased">2019-09-03 18:35:13</date>
              <date type="whenProduced">2019-08</date>
              <date type="whenEndEmbargoed">2019-09-03</date>
              <ref type="file" target="https://hal.sorbonne-universite.fr/hal-02277646v1/document">
                <date notBefore="2019-09-03"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.sorbonne-universite.fr/hal-02277646v1/file/1702.00156.pdf" id="file-2277646-2198961">
                <date notBefore="2019-09-03"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1702.00156"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="651455">
                <persName>
                  <forename>Gestionnaire HAL 3</forename>
                  <surname>Sorbonne Université</surname>
                </persName>
                <email type="md5">a829e169d53d985531a4db19c33011d6</email>
                <email type="domain">sorbonne-universite.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02277646</idno>
            <idno type="halUri">https://hal.sorbonne-universite.fr/hal-02277646</idno>
            <idno type="halBibtex">dutta:hal-02277646</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE Transactions on Neural Networks and Learning Systems&lt;/i&gt;, 2019, 30 (8), pp.2369-2382. &lt;a target="_blank" href="https://dx.doi.org/10.1109/TNNLS.2018.2884700"&gt;&amp;#x27E8;10.1109/TNNLS.2018.2884700&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE Transactions on Neural Networks and Learning Systems, 2019, 30 (8), pp.2369-2382. &amp;#x27E8;10.1109/TNNLS.2018.2884700&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2277646-2198961"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LIP6" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique de Paris 6</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="SUPRA_MATHS_INFO">Mathématiques + Informatique</idno>
          </seriesStmt>
          <notesStmt>
            <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">Stochastic Graphlet Embedding</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Anjan</forename>
                    <surname>Dutta</surname>
                  </persName>
                  <idno type="halauthorid">732255-0</idno>
                  <affiliation ref="#struct-19095"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hichem</forename>
                    <surname>Sahbi</surname>
                  </persName>
                  <email type="md5">bd06ee81c3ee1dee3fcba8b296500031</email>
                  <email type="domain">lip6.fr</email>
                  <idno type="idhal" notation="string">hichem-sahbi</idno>
                  <idno type="idhal" notation="numeric">742003</idno>
                  <idno type="halauthorid" notation="string">52390-742003</idno>
                  <idno type="IDREF">https://www.idref.fr/077125223</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6813-9146</idno>
                  <affiliation ref="#struct-541720"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">81027</idno>
                <idno type="issn">2162-237X</idno>
                <title level="j">IEEE Transactions on Neural Networks and Learning Systems</title>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="volume">30</biblScope>
                  <biblScope unit="issue">8</biblScope>
                  <biblScope unit="pp">2369-2382</biblScope>
                  <date type="datePub">2019-08</date>
                  <date type="dateEpub">2018-12-24</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1702.00156</idno>
              <idno type="doi">10.1109/TNNLS.2018.2884700</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Graph hashing</term>
                <term xml:lang="en">Graph classification</term>
                <term xml:lang="en">Graph embedding</term>
                <term xml:lang="en">Stochastic graphlets</term>
                <term xml:lang="en">Betweenness centrality</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cv">Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]</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>Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments, etc.) and edges characterize the relationships between these primitives. However, these non-vectorial graph data cannot be straightforwardly plugged into off-the-shelf machine learning algorithms without a preliminary step of-explicit/implicit-graph vectorization and embedding. This embedding process should be resilient to intra-class graph variations while being highly discriminant. In this paper, we propose a novel high-order stochastic graphlet embedding (SGE) that maps graphs into vector spaces. Our main contribution includes a new stochastic search procedure that efficiently parses a given graph and extracts/samples unlimitedly high-order graphlets. We consider these graphlets, with increasing orders, to model local primitives as well as their increasingly complex interactions. In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision. When combined with maximum margin classifiers, these graphlet-based representations have positive impact on the performance of pattern comparison and recognition as corroborated through extensive experiments using standard benchmark databases.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-19095" status="VALID">
          <orgName>Computer Vision Center (Centre de visio per computador)</orgName>
          <orgName type="acronym">CVC</orgName>
          <desc>
            <address>
              <addrLine>Edifici O - Campus UAB - 08193 Bellaterra (Cerdanyola) - Barcelona, Spain</addrLine>
              <country key="ES"/>
            </address>
            <ref type="url">http://www.cvc.uab.es/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-98227" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-541720" status="OLD">
          <orgName>Machine Learning and Information Access</orgName>
          <orgName type="acronym">MLIA</orgName>
          <date type="start">2018-01-01</date>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-541703" type="direct"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation name="UMR7606" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-98227" status="VALID">
          <idno type="ISNI">0000 0001 2296 0625</idno>
          <idno type="ROR">https://ror.org/052g8jq94</idno>
          <orgName>Universitat Autònoma de Barcelona = Autonomous University of Barcelona = Universidad Autónoma de Barcelona</orgName>
          <orgName type="acronym">UAB</orgName>
          <date type="start">1968-01-01</date>
          <desc>
            <address>
              <addrLine>UAB Campus 08193 Bellaterra Barcelona</addrLine>
              <country key="ES"/>
            </address>
            <ref type="url">https://www.uab.cat/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-541703" status="VALID">
          <idno type="IdRef">13558292X</idno>
          <idno type="RNSR">199712651U</idno>
          <idno type="ROR">https://ror.org/05krcen59</idno>
          <orgName>LIP6</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>4 Place JUSSIEU 75252 PARIS CEDEX 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lip6.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-413221" type="direct"/>
            <relation name="UMR7606" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.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>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-33739" status="VALID">
          <idno type="anr">ANR-11-BS02-0017</idno>
          <idno type="program">BLANC</idno>
          <orgName>MLVIS</orgName>
          <desc>Apprentissage Automatique pour l'annotation visuelle dans les media sociaux</desc>
          <date type="start">2011</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>