<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>10045</id>
    <completedYear/>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>reportzib</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2025-06-11</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Similarity-based fuzzy clustering scientific articles: potentials and challenges from mathematical and computational perspectives</title>
    <abstract language="eng">Fuzzy clustering, which allows an article to belong to multiple clusters with soft membership degrees, plays a vital role in analyzing publication data. This problem can be formulated as a constrained optimization model, where the goal is to minimize the discrepancy between the similarity observed from data and the similarity derived from a predicted distribution. While this approach benefits from leveraging state-of-the-art optimization algorithms, tailoring them to work with real, massive databases like OpenAlex or Web of Science -- containing about 70 million articles and a billion citations -- poses significant challenges. We analyze potentials and challenges of the approach from both mathematical and computational perspectives. Among other things, second-order optimality conditions are established, providing new theoretical insights, and practical solution methods are proposed by exploiting the problem’s structure. Specifically, we accelerate the gradient projection method using GPU-based parallel computing to efficiently handle large-scale data.</abstract>
    <identifier type="url">https://opus4.kobv.de/opus4-zib/frontdoor/index/index/docId/10036</identifier>
    <identifier type="arxiv">2506.04045</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <author>Thi Huong Vu</author>
    <submitter>Thi Huong Vu</submitter>
    <author>Ida Litzel</author>
    <author>Thorsten Koch</author>
    <series>
      <title>ZIB-Report</title>
      <number>25-09</number>
    </series>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>bibliometrics</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>fuzzy clustering</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>large-scale publication data</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>non-convex optimization</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>second-order optimality</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>gradient projection methods</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Nesterov acceleration</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>GPU-based parallel computing</value>
    </subject>
    <collection role="msc" number="62H30">Classification and discrimination; cluster analysis [See also 68T10]</collection>
    <collection role="msc" number="68T05">Learning and adaptive systems [See also 68Q32, 91E40]</collection>
    <collection role="msc" number="68W10">Parallel algorithms</collection>
    <collection role="msc" number="90C26">Nonconvex programming, global optimization</collection>
    <collection role="msc" number="90C30">Nonlinear programming</collection>
    <collection role="msc" number="90C90">Applications of mathematical programming</collection>
    <collection role="institutes" number="sis">Digital Data and Information for Society, Science, and Culture</collection>
    <collection role="institutes" number="">KOBV</collection>
    <collection role="persons" number="koch">Koch, Thorsten</collection>
    <collection role="projects" number="MODAL-Gesamt">MODAL-Gesamt</collection>
    <collection role="institutes" number="aim">Applied Algorithmic Intelligence Methods</collection>
    <collection role="projects" number="MODAL-EnergyLab">MODAL-EnergyLab</collection>
    <collection role="persons" number="huong.vu">Vu, Thi Huong</collection>
    <collection role="projects" number="FAN">FAN</collection>
    <collection role="institutes" number="aopt">Applied Optimization</collection>
    <file>https://opus4.kobv.de/opus4-zib/files/10045/Huong_Litzel_Koch_ZIBreport2509</file>
  </doc>
</export-example>
