<?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-04930772</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="2026-05-19T04:00:20+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A comprehensive investigation of variational auto-encoders for population synthesis</title>
            <author role="aut">
              <persName>
                <forename type="first">Abdoul Razac</forename>
                <surname>Sané</surname>
              </persName>
              <email type="md5">9f18ba00a324f54d26fd828183e4b3c4</email>
              <email type="domain">yahoo.com</email>
              <idno type="idhal" notation="string">abdoulrazacsane</idno>
              <idno type="idhal" notation="numeric">1439525</idno>
              <idno type="halauthorid" notation="string">3402330-1439525</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8619-0962</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=HaAD02UAAAAJ</idno>
              <affiliation ref="#struct-581153"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pierre-Olivier</forename>
                <surname>Vandanjon</surname>
              </persName>
              <email type="md5">fcd9206212adf337398d7d8f76b837d5</email>
              <email type="domain">univ-eiffel.fr</email>
              <idno type="idhal" notation="string">pierre-olivier-vandanjon</idno>
              <idno type="idhal" notation="numeric">20595</idno>
              <idno type="halauthorid" notation="string">27161-20595</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1833-4669</idno>
              <idno type="IDREF">https://www.idref.fr/104533811</idno>
              <affiliation ref="#struct-581153"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Rachid</forename>
                <surname>Belaroussi</surname>
              </persName>
              <email type="md5">b16e17a9c7cbee0feedca41f04745234</email>
              <email type="domain">univ-eiffel.fr</email>
              <idno type="idhal" notation="numeric">1233055</idno>
              <idno type="halauthorid" notation="string">429322-1233055</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8783-1226</idno>
              <affiliation ref="#struct-580990"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pierre</forename>
                <surname>Hankach</surname>
              </persName>
              <email type="md5">d25409bfdb0cac8995eb8d7908ae99fb</email>
              <email type="domain">univ-eiffel.fr</email>
              <idno type="idhal" notation="string">pierrehankach</idno>
              <idno type="idhal" notation="numeric">1258560</idno>
              <idno type="halauthorid" notation="string">496462-1258560</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4333-716X</idno>
              <affiliation ref="#struct-581019"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Abdoul Razac</forename>
                <surname>SANE</surname>
              </persName>
              <email type="md5">7e8adf1beabb5a58798d57cd51c223cd</email>
              <email type="domain">univ-eiffel.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-02-05 14:24:41</date>
              <date type="whenModified">2025-12-18 10:06:36</date>
              <date type="whenReleased">2025-02-05 16:02:27</date>
              <date type="whenProduced">2025-01-01</date>
              <date type="whenEndEmbargoed">2025-05-11</date>
              <ref type="file" target="https://univ-eiffel.hal.science/hal-04930772v1/document">
                <date notBefore="2025-05-11"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://univ-eiffel.hal.science/hal-04930772v1/file/Abdoul-Razac-SANE-2024-Article-JCSS.pdf" id="file-4930772-4279454">
                <date notBefore="2025-05-11"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1597991">
                <persName>
                  <forename>Abdoul Razac</forename>
                  <surname>SANE</surname>
                </persName>
                <email type="md5">7e8adf1beabb5a58798d57cd51c223cd</email>
                <email type="domain">univ-eiffel.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04930772</idno>
            <idno type="halUri">https://univ-eiffel.hal.science/hal-04930772</idno>
            <idno type="halBibtex">sane:hal-04930772</idno>
            <idno type="halRefHtml">&lt;i&gt;Journal of Computational Social Science&lt;/i&gt;, 2025, 8, pp.13. &lt;a target="_blank" href="https://dx.doi.org/10.1007/s42001-024-00332-0"&gt;&amp;#x27E8;10.1007/s42001-024-00332-0&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Journal of Computational Social Science, 2025, 8, pp.13. &amp;#x27E8;10.1007/s42001-024-00332-0&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4930772-4279454"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="IFSTTAR">Ifsttar</idno>
            <idno type="stamp" n="UNIV-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="U-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="AME">Aménagement, Mobilités et Environnement</idno>
            <idno type="stamp" n="COSYS">Composants et systèmes</idno>
            <idno type="stamp" n="MAST">Matériaux et Structures</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">A comprehensive investigation of variational auto-encoders for population synthesis</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Abdoul Razac</forename>
                    <surname>Sané</surname>
                  </persName>
                  <email type="md5">9f18ba00a324f54d26fd828183e4b3c4</email>
                  <email type="domain">yahoo.com</email>
                  <idno type="idhal" notation="string">abdoulrazacsane</idno>
                  <idno type="idhal" notation="numeric">1439525</idno>
                  <idno type="halauthorid" notation="string">3402330-1439525</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8619-0962</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=HaAD02UAAAAJ</idno>
                  <affiliation ref="#struct-581153"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre-Olivier</forename>
                    <surname>Vandanjon</surname>
                  </persName>
                  <email type="md5">fcd9206212adf337398d7d8f76b837d5</email>
                  <email type="domain">univ-eiffel.fr</email>
                  <idno type="idhal" notation="string">pierre-olivier-vandanjon</idno>
                  <idno type="idhal" notation="numeric">20595</idno>
                  <idno type="halauthorid" notation="string">27161-20595</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1833-4669</idno>
                  <idno type="IDREF">https://www.idref.fr/104533811</idno>
                  <affiliation ref="#struct-581153"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Rachid</forename>
                    <surname>Belaroussi</surname>
                  </persName>
                  <email type="md5">b16e17a9c7cbee0feedca41f04745234</email>
                  <email type="domain">univ-eiffel.fr</email>
                  <idno type="idhal" notation="numeric">1233055</idno>
                  <idno type="halauthorid" notation="string">429322-1233055</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8783-1226</idno>
                  <affiliation ref="#struct-580990"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre</forename>
                    <surname>Hankach</surname>
                  </persName>
                  <email type="md5">d25409bfdb0cac8995eb8d7908ae99fb</email>
                  <email type="domain">univ-eiffel.fr</email>
                  <idno type="idhal" notation="string">pierrehankach</idno>
                  <idno type="idhal" notation="numeric">1258560</idno>
                  <idno type="halauthorid" notation="string">496462-1258560</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4333-716X</idno>
                  <affiliation ref="#struct-581019"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">149451</idno>
                <idno type="issn">2432-2717</idno>
                <idno type="eissn">2432-2725</idno>
                <title level="j">Journal of Computational Social Science</title>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="volume">8</biblScope>
                  <biblScope unit="pp">13</biblScope>
                  <date type="datePub">2025-01-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/s42001-024-00332-0</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Synthetic population</term>
                <term xml:lang="en">machine learning</term>
                <term xml:lang="en">deep generative model</term>
                <term xml:lang="en">variational autoencoders</term>
                <term xml:lang="en">sampling zeros</term>
                <term xml:lang="en">structural zeros</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="math">Mathematics [math]</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>The use of synthetic populations has grown considerably over the recent years, in revolutionizing studies conducted within various fields, including social science research, urban planning, public health and transportation modeling. These synthetic populations prove to be valuable, as substitutes for the often missing or sensitive real data, and moreover are capable of preserving both privacy and representativeness. They are typically constructed from aggregate and/or sample data. Recently, new methods for generating synthetic populations based on deep learning, notably Variational Autoencoders (VAEs), have been developed. Such methods serve to overcome the limitations of traditional methods, such as Iterative Proportional Fitting (IPF), which are unable to generate agents with cross-modalities not found in the sample data. As such, IPF requires large samples to generate a synthetic population closely resembling the actual one. Conversely, the advantage of VAE lies in their ability to generate agents not found in the sample data, albeit with the risk of creating agents not existing in the actual population. However, the practical documentation as well as detailed analyses of the architectures and results from implementation of these deep learning approaches, in particular VAE, are limited, thus making these methods difficult to appropriate for practitioners. This paper focuses on generating synthetic populations using VAE. First, an in-depth and accessible theoretical explanation of how VAEs function is provided. Next, a detailed study of these methods is carried out by testing the various architectures, parameters, sample sizes and evaluation indicators necessary to guarantee high-quality results. Highlighted herein is the ability of VAEs to generate large datasets with a small training sample, in addition to VAE performance in generating new realistic individuals not present in the learning base. Certain limitations are identified, including the difficulties encountered by VAEs in managing numerical attributes and the need for post-processing to eliminate unrealistic individuals. In conclusion, despite a number of limitations, VAE constitutes a very promising methodology for generating synthetic populations, in offering practitioners numerous advantages. This paper is accompanied by a Python notebook to assist interested readers implement this new methodology.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-581153" status="VALID">
          <idno type="IdRef">154956600</idno>
          <idno type="RNSR">200518203U</idno>
          <orgName>Systèmes Productifs, Logistique, Organisation des Transports et Travail</orgName>
          <orgName type="acronym">AME-SPLOTT</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>14-20 Boulevard Newton Cité Descartes, Champs sur Marne F-77454 Marne la Vallée</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.splott.ifsttar.fr/linstitut/ame/laboratoires/splott/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-580722" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-580990" status="VALID">
          <idno type="IdRef">161309690</idno>
          <idno type="RNSR">198518204G</idno>
          <orgName>Génie des Réseaux de Transport Terrestres et Informatique Avancée</orgName>
          <orgName type="acronym">COSYS-GRETTIA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>14-20 Boulevard NewtonCité Descartes, Champs sur MarneF-77454  Marne la Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ifsttar.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-580722" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-581019" status="VALID">
          <orgName>Laboratoire Auscultation, Modélisation, Expérimentation des infrastructures de transport</orgName>
          <orgName type="acronym">MAST-LAMES</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Allée des Ponts et Chaussées Route de Bouaye 44344 Bouguenais Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ifsttar.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-580722" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-580722" status="VALID">
          <idno type="ROR">https://ror.org/03x42jk29</idno>
          <orgName>Université Gustave Eiffel</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Cité Descartes, 5 Boulevard Descartes • Champs-sur-Marne, 77454 Marne-la-Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-gustave-eiffel.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>