Skip to main navigation Skip to search Skip to main content

A Two-Stage Multi-Source Transfer Learning Approach for Software Defect Prediction

  • Hao Li
  • , Shuo Wang*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

105 Downloads (Pure)

Abstract

Multi-source transfer learning (MSTL) acquires knowledge from multiple source domains to improve learning in a target domain, offering higher generalization and robustness than single-source transfer. In software defect prediction, MSTL utilizes cross-project data for more accurate prediction. However, existing methods often neglect the scarcity of defect samples in the target domain. To address this, we propose Cross-Domain Consistency Multisource Transfer Learning (CDC-MSTL), a novel ensemble method based on MsTrAdaBoost. CDC-MSTL considers both domain similarity through two-stage instance transfer and the target dataset’s imbalance degree during training. Experiments on four software projects (23 datasets) show CDC-MSTL significantly outperforms state-of-the-art MSTL methods in Balanced Accuracy (BA) and is competitive in AUC, F-measure, and accuracy.
Original languageEnglish
Title of host publication2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Electronic)9798331511210
ISBN (Print)9798331511227
DOIs
Publication statusPublished - 6 Jan 2026
Event23rd IEEE International Conference on Industrial Informatics - KunMing, China
Duration: 12 Jul 2025 → 15 Jul 2025
Conference number: 23
https://indin2025.ieee-ies.org/#/home

Publication series

NameIEEE International Conference on Industrial Informatics (INDIN)
PublisherIEEE
ISSN (Print)1935-4576
ISSN (Electronic)2378-363X

Conference

Conference23rd IEEE International Conference on Industrial Informatics
Abbreviated titleINDIN 2025
Country/TerritoryChina
CityKunMing
Period12/07/25 → 15/07/25
Internet address

Fingerprint

Dive into the research topics of 'A Two-Stage Multi-Source Transfer Learning Approach for Software Defect Prediction'. Together they form a unique fingerprint.

Cite this