Academic Journal
View in EDS

Neural acceleration of graph partitioning

Bibliographic Details
Title: Neural acceleration of graph partitioning
Authors: Patel, Vishvam
Source: Theses
Publisher Information: LOUIS
Publication Year: 2025
Subject Terms: Graph partitioning, Neural acceleration, Spectral methods, Graph theory--Data processing, Partitions (Mathematics), Neural networks (Computer science)
Description: Graph Partitioning is a critical problem in numerous scientific and engineering domains including social network analysis, VLSI design, and many more. Spectral methods are known to produce quality partitions while minimizing edge cuts for a wide range of problems. However, the computational cost associated with the calculation of the Fiedler vector, an eigenvector associated with the second smallest eigenvalue of the graph Laplacian, remains a significant bottleneck. In this paper, we present an neural acceleration approach to spectral bisection partitioning by replacing the traditional eigenvalue calculation with a simple artificial neural network model to approximate the fiedler vector. We demonstrate that our approach achieves partitioning quality comparable to spectral bisection while significantly reducing the computational overhead, making it more scalable and efficient for large-scale problems.
Document Type: text
File Description: application/pdf
Language: unknown
Availability: https://louis.uah.edu/uah-theses/744
https://louis.uah.edu/context/uah-theses/article/1751/viewcontent/patelvishvam_11109.pdf
Accession Number: edsbas.2363F68C
Database: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://louis.uah.edu/uah-theses/744#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.2363F68C
RelevancyScore: 908
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 907.8095703125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Neural acceleration of graph partitioning
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Patel%2C+Vishvam%22">Patel, Vishvam</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Theses
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: LOUIS
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Graph+partitioning%22">Graph partitioning</searchLink><br /><searchLink fieldCode="DE" term="%22Neural+acceleration%22">Neural acceleration</searchLink><br /><searchLink fieldCode="DE" term="%22Spectral+methods%22">Spectral methods</searchLink><br /><searchLink fieldCode="DE" term="%22Graph+theory--Data+processing%22">Graph theory--Data processing</searchLink><br /><searchLink fieldCode="DE" term="%22Partitions+%28Mathematics%29%22">Partitions (Mathematics)</searchLink><br /><searchLink fieldCode="DE" term="%22Neural+networks+%28Computer+science%29%22">Neural networks (Computer science)</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Graph Partitioning is a critical problem in numerous scientific and engineering domains including social network analysis, VLSI design, and many more. Spectral methods are known to produce quality partitions while minimizing edge cuts for a wide range of problems. However, the computational cost associated with the calculation of the Fiedler vector, an eigenvector associated with the second smallest eigenvalue of the graph Laplacian, remains a significant bottleneck. In this paper, we present an neural acceleration approach to spectral bisection partitioning by replacing the traditional eigenvalue calculation with a simple artificial neural network model to approximate the fiedler vector. We demonstrate that our approach achieves partitioning quality comparable to spectral bisection while significantly reducing the computational overhead, making it more scalable and efficient for large-scale problems.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: text
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: unknown
– Name: URL
  Label: Availability
  Group: URL
  Data: https://louis.uah.edu/uah-theses/744<br />https://louis.uah.edu/context/uah-theses/article/1751/viewcontent/patelvishvam_11109.pdf
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.2363F68C
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.2363F68C
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: unknown
    Subjects:
      – SubjectFull: Graph partitioning
        Type: general
      – SubjectFull: Neural acceleration
        Type: general
      – SubjectFull: Spectral methods
        Type: general
      – SubjectFull: Graph theory--Data processing
        Type: general
      – SubjectFull: Partitions (Mathematics)
        Type: general
      – SubjectFull: Neural networks (Computer science)
        Type: general
    Titles:
      – TitleFull: Neural acceleration of graph partitioning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Patel, Vishvam
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsbas
          Titles:
            – TitleFull: Theses
              Type: main
ResultId 1