scholarly journals Conditional Domain Adversarial Adaptation for Heterogeneous Defect Prediction

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 150738-150749
Author(s):  
Lina Gong ◽  
Shujuan Jiang ◽  
Li Jiang
Keyword(s):  
Defect Prediction ◽  
Heterogeneous Defect Prediction

scholarly journals Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction

2019 ◽  
Vol E102.D (3) ◽  
pp. 537-549 ◽  
Author(s):  
Lina GONG ◽  
Shujuan JIANG ◽  
Qiao YU ◽  
Li JIANG
Keyword(s):  
Domain Adaptation ◽  
Defect Prediction ◽  
Heterogeneous Defect Prediction

Semi-supervised Heterogeneous Defect Prediction with Open-source Projects on GitHub

2021 ◽  
Vol 31 (06) ◽  
pp. 889-916
Author(s):  
Ying Sun ◽  
Xiao-Yuan Jing ◽  
Fei Wu ◽  
Xiwei Dong ◽  
Yanfei Sun ◽  
...  
Keyword(s):  
Correlation Analysis ◽  
Open Source ◽  
Large Scale ◽  
Real Life ◽  
Defect Prediction ◽  
Public Project ◽  
Research Attention ◽  
Target Company ◽  
Public Datasets ◽  
Heterogeneous Defect Prediction

The heterogeneous defect prediction (HDP) technique can predict defects in a target company using heterogeneous metric data from external company, which has received substantial research attention. However, existing HDP methods assume that source data is labeled but labeling data is expensive. Semi-supervised defect prediction technique can perform defect prediction with few labeled data. In this paper, we investigate a new problem — semi-supervised HDP (SHDP). To solve this problem, we propose a new approach named cost-sensitive kernel semi-supervised correlation analysis (CKSCA) as a solution of SHDP problem. It introduces unified metric representation and canonical correlation analysis to make the data distributions of different company projects more similar. CKSCA also designs a cost-sensitive kernel semi-supervised discriminant analysis mechanism to utilize the limited labeled data and sufficient real-life unlabeled data from different companies. Besides we collect lots of open-source projects from GitHub website to construct a new large-scale unlabeled dataset called GITHUB dataset. It contains 26,407 modules and is greater than each public project dataset. It has been public online and can be extended continuously. Experiments on the GITHUB dataset and other public datasets indicate that unlabeled GITHUB data can help prediction model improve prediction performance, and CKSCA is effective and efficient for solving SHDP problem.

scholarly journals Heterogeneous Defect Prediction

2018 ◽  
Vol 44 (9) ◽  
pp. 874-896 ◽  
Author(s):  
Jaechang Nam ◽  
Wei Fu ◽  
Sunghun Kim ◽  
Tim Menzies ◽  
Lin Tan
Keyword(s):  
Defect Prediction ◽  
Heterogeneous Defect Prediction

scholarly journals Few-Shot Learning Based Balanced Distribution Adaptation for Heterogeneous Defect Prediction

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 32989-33001 ◽  
Author(s):  
Aili Wang ◽  
Yutong Zhang ◽  
Haibin Wu ◽  
Kaiyuan Jiang ◽  
Minhui Wang
Keyword(s):  
Defect Prediction ◽  
Balanced Distribution ◽  
Heterogeneous Defect Prediction

On the Multiple Sources and Privacy Preservation Issues for Heterogeneous Defect Prediction

2019 ◽  
Vol 45 (4) ◽  
pp. 391-411 ◽  
Author(s):  
Zhiqiang Li ◽  
Xiao-Yuan Jing ◽  
Xiaoke Zhu ◽  
Hongyu Zhang ◽  
Baowen Xu ◽  
...  
Keyword(s):  
Privacy Preservation ◽  
Defect Prediction ◽  
Multiple Sources ◽  
Heterogeneous Defect Prediction
Sign in / Sign up

Export Citation Format

Share Document