<?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-03228070</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="2026-05-03T09:10:50+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">End-to-End Similarity Learning and Hierarchical Clustering for unfixed size datasets</title>
            <author role="aut">
              <persName>
                <forename type="first">Leonardo</forename>
                <surname>Gigli</surname>
              </persName>
              <idno type="halauthorid">1501924-0</idno>
              <affiliation ref="#struct-206"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Beatriz</forename>
                <surname>Marcotegui</surname>
              </persName>
              <email type="md5">7c561221c75b46f981b86916c4884581</email>
              <email type="domain">mines-paristech.fr</email>
              <idno type="idhal" notation="string">beatriz-marcotegui</idno>
              <idno type="idhal" notation="numeric">6795</idno>
              <idno type="halauthorid" notation="string">11043-6795</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2825-7292</idno>
              <idno type="IDREF">https://www.idref.fr/130440531</idno>
              <affiliation ref="#struct-206"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Santiago</forename>
                <surname>Velasco-Forero</surname>
              </persName>
              <email type="md5">9c19077c2898347ced4d638bd1a37b18</email>
              <email type="domain">minesparis.psl.eu</email>
              <idno type="idhal" notation="string">velascoforero</idno>
              <idno type="idhal" notation="numeric">4198</idno>
              <idno type="halauthorid" notation="string">18018-4198</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2438-1747</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=l3-z3GMAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/169108589</idno>
              <affiliation ref="#struct-206"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Santiago</forename>
                <surname>Velasco-Forero</surname>
              </persName>
              <email type="md5">9c19077c2898347ced4d638bd1a37b18</email>
              <email type="domain">minesparis.psl.eu</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-05-17 18:06:58</date>
              <date type="whenModified">2026-01-09 09:48:30</date>
              <date type="whenReleased">2021-05-21 17:29:47</date>
              <date type="whenProduced">2021-07-21</date>
              <date type="whenEndEmbargoed">2021-05-17</date>
              <ref type="file" target="https://hal.science/hal-03228070v1/document">
                <date notBefore="2021-05-17"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03228070v1/file/GSI2021_Gigli.pdf" id="file-3228070-2834354">
                <date notBefore="2021-05-17"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="148574">
                <persName>
                  <forename>Santiago</forename>
                  <surname>Velasco-Forero</surname>
                </persName>
                <email type="md5">9c19077c2898347ced4d638bd1a37b18</email>
                <email type="domain">minesparis.psl.eu</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03228070</idno>
            <idno type="halUri">https://hal.science/hal-03228070</idno>
            <idno type="halBibtex">gigli:hal-03228070</idno>
            <idno type="halRefHtml">&lt;i&gt;5th conference on Geometric Science of Information&lt;/i&gt;, Jul 2021, Paris, France</idno>
            <idno type="halRef">5th conference on Geometric Science of Information, Jul 2021, Paris, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3228070-2834354"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="ENSMP" corresp="PARISTECH">MINES ParisTech</idno>
            <idno type="stamp" n="ENSMP_CMM" corresp="ENSMP">Morphologie mathématique (CMM)</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="TDS-MACS">Réseau de recherche en Théorie des Systèmes Distribués, Modélisation, Analyse et Contrôle des Systèmes</idno>
            <idno type="stamp" n="PSL">Université Paris sciences et lettres</idno>
            <idno type="stamp" n="ENSMP_DEP_MS">Département Mathématiques et systèmes</idno>
            <idno type="stamp" n="ENSMP_DR" corresp="ENSMP">ENSMP_DR</idno>
            <idno type="stamp" n="ENSMP-PSL" corresp="PSL">MINES ParisTech - École nationale supérieure des mines de Paris - PSL</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">End-to-End Similarity Learning and Hierarchical Clustering for unfixed size datasets</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Leonardo</forename>
                    <surname>Gigli</surname>
                  </persName>
                  <idno type="halauthorid">1501924-0</idno>
                  <affiliation ref="#struct-206"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Beatriz</forename>
                    <surname>Marcotegui</surname>
                  </persName>
                  <email type="md5">7c561221c75b46f981b86916c4884581</email>
                  <email type="domain">mines-paristech.fr</email>
                  <idno type="idhal" notation="string">beatriz-marcotegui</idno>
                  <idno type="idhal" notation="numeric">6795</idno>
                  <idno type="halauthorid" notation="string">11043-6795</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2825-7292</idno>
                  <idno type="IDREF">https://www.idref.fr/130440531</idno>
                  <affiliation ref="#struct-206"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Santiago</forename>
                    <surname>Velasco-Forero</surname>
                  </persName>
                  <email type="md5">9c19077c2898347ced4d638bd1a37b18</email>
                  <email type="domain">minesparis.psl.eu</email>
                  <idno type="idhal" notation="string">velascoforero</idno>
                  <idno type="idhal" notation="numeric">4198</idno>
                  <idno type="halauthorid" notation="string">18018-4198</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2438-1747</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=l3-z3GMAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/169108589</idno>
                  <affiliation ref="#struct-206"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>5th conference on Geometric Science of Information</title>
                  <date type="start">2021-07-21</date>
                  <settlement>Paris</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="spi.signal">Engineering Sciences [physics]/Signal and Image processing</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-dm">Computer Science [cs]/Discrete Mathematics [cs.DM]</classCode>
              <classCode scheme="halDomain" n="info.info-ti">Computer Science [cs]/Image Processing [eess.IV]</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halDomain" n="stat.ap">Statistics [stat]/Applications [stat.AP]</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>Hierarchical clustering (HC) is a powerful tool in data analysis since it allows discovering patterns in the observed data at different scales. Similarity-based HC methods take as input a fixed number of points and the matrix of pairwise similarities and output the dendrogram representing the nested partition. However, in some cases, the entire dataset cannot be known in advance and thus neither the relations between the points. In this paper, we consider the case in which we have a collection of realizations of a random distribution, and we want to extract a hierarchical clustering for each sample. The number of elements varies at each draw. Based on a continuous relaxation of Dasgupta's cost function, we propose to integrate a triplet loss function to Chami's formulation in order to learn an optimal similarity function between the points to use to compute the optimal hierarchy. Two architectures are tested on four datasets as approximators of the similarity function. The results obtained are promising and the proposed method showed in many cases good robustness to noise and higher adaptability to different datasets compared with the classical approaches.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-206" status="VALID">
          <idno type="IdRef">15213493X</idno>
          <idno type="ROR">https://ror.org/0579t4s85</idno>
          <orgName>Centre de Morphologie Mathématique</orgName>
          <orgName type="acronym">CMM</orgName>
          <date type="end">2025-12-31</date>
          <desc>
            <address>
              <addrLine>35 rue Saint-Honoré 77305 Fontainebleau cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cmm.mines-paristech.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301492" type="direct"/>
            <relation active="#struct-564132" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301492" status="VALID">
          <idno type="IdRef">026375249</idno>
          <idno type="ROR">https://ror.org/04y8cs423</idno>
          <orgName>Mines Paris - PSL (École nationale supérieure des mines de Paris)</orgName>
          <date type="start">1783-01-01</date>
          <desc>
            <address>
              <addrLine>60, boulevard Saint-Michel 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.minesparis.psl.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-564132" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-564132" status="VALID">
          <idno type="IdRef">241597595</idno>
          <idno type="ISNI">0000 0004 1784 3645</idno>
          <idno type="ROR">https://ror.org/013cjyk83</idno>
          <orgName>Université Paris Sciences et Lettres</orgName>
          <orgName type="acronym">PSL</orgName>
          <desc>
            <address>
              <addrLine>60 rue Mazarine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.psl.eu/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>