View in EDS

DP‐GCN: Integrating GraphCodeBERT and GCN With Contrastive Learning for Software Defect Prediction.

Saved in:
Bibliographic Details
Title: DP‐GCN: Integrating GraphCodeBERT and GCN With Contrastive Learning for Software Defect Prediction.
Authors: Liu, Xueting1 (AUTHOR) 2193745755@qq.com, Jin, Haibo1 (AUTHOR)
Source: Journal of Software: Evolution & Process. Apr2026, Vol. 38 Issue 4, p1-17. 17p.
Subjects: Defect tracking (Computer software development), Graph neural networks, Machine learning, Generalization
Abstract: Software defect prediction identifies high‐risk code early, reducing development costs and improving software quality. Early studies primarily relied on handcrafted features, which struggled to capture semantic differences and structural information within programs. Later research fused semantic features extracted from abstract syntax trees (ASTs) or graph structures with handcrafted features, improving prediction performance. However, existing fusion methods still face challenges such as insufficient deep semantic mining, inadequate global dependency capture, and weak cross‐project generalization. To address these limitations, this paper proposes DP‐GCN, a defect prediction model integrating GraphCodeBERT, graph convolutional network (GCN), and contrastive learning. Specifically, GraphCodeBERT extracts semantic and structural code representations, GCN captures global dependencies among code elements, and contrastive learning optimizes the feature space distribution to enhance discriminability. The optimized deep features are then fused with handcrafted features and fed into a logistic regression classifier for defect prediction. Experiments on 10 projects from the PROMISE dataset show that DP‐GCN outperforms existing methods in both within‐project and cross‐project scenarios, validating its effectiveness and the synergistic advantages of the three integrated techniques. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Software: Evolution & Process is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 193280461
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: DP‐GCN: Integrating GraphCodeBERT and GCN With Contrastive Learning for Software Defect Prediction.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Liu%2C+Xueting%22">Liu, Xueting</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 2193745755@qq.com</i><br /><searchLink fieldCode="AR" term="%22Jin%2C+Haibo%22">Jin, Haibo</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Software%3A+Evolution+%26+Process%22">Journal of Software: Evolution & Process</searchLink>. Apr2026, Vol. 38 Issue 4, p1-17. 17p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Defect+tracking+%28Computer+software+development%29%22">Defect tracking (Computer software development)</searchLink><br /><searchLink fieldCode="DE" term="%22Graph+neural+networks%22">Graph neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Generalization%22">Generalization</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Software defect prediction identifies high‐risk code early, reducing development costs and improving software quality. Early studies primarily relied on handcrafted features, which struggled to capture semantic differences and structural information within programs. Later research fused semantic features extracted from abstract syntax trees (ASTs) or graph structures with handcrafted features, improving prediction performance. However, existing fusion methods still face challenges such as insufficient deep semantic mining, inadequate global dependency capture, and weak cross‐project generalization. To address these limitations, this paper proposes DP‐GCN, a defect prediction model integrating GraphCodeBERT, graph convolutional network (GCN), and contrastive learning. Specifically, GraphCodeBERT extracts semantic and structural code representations, GCN captures global dependencies among code elements, and contrastive learning optimizes the feature space distribution to enhance discriminability. The optimized deep features are then fused with handcrafted features and fed into a logistic regression classifier for defect prediction. Experiments on 10 projects from the PROMISE dataset show that DP‐GCN outperforms existing methods in both within‐project and cross‐project scenarios, validating its effectiveness and the synergistic advantages of the three integrated techniques. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Software: Evolution & Process is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193280461
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/smr.70116
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 1
    Subjects:
      – SubjectFull: Defect tracking (Computer software development)
        Type: general
      – SubjectFull: Graph neural networks
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Generalization
        Type: general
    Titles:
      – TitleFull: DP‐GCN: Integrating GraphCodeBERT and GCN With Contrastive Learning for Software Defect Prediction.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu, Xueting
      – PersonEntity:
          Name:
            NameFull: Jin, Haibo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20477473
          Numbering:
            – Type: volume
              Value: 38
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Journal of Software: Evolution & Process
              Type: main
ResultId 1