IEICE TRANSACTIONS on Information
Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction
Summary :
Heterogeneous defect prediction (HDP) is to detect the largest number of defective software modules in one project by using historical data collected from other projects with different metrics. However, these data can not be directly used because of different metrics set among projects. Meanwhile, software data have more non-defective instances than defective instances which may cause a significant bias towards defective instances. To completely solve these two restrictions, we propose unsupervised deep domain adaptation approach to build a HDP model. Specifically, we firstly map the data of source and target projects into a unified metric representation (UMR). Then, we design a simple neural network (SNN) model to deal with the heterogeneous and class-imbalanced problems in software defect prediction (SDP). In particular, our model introduces the Maximum Mean Discrepancy (MMD) as the distance between the source and target data to reduce the distribution mismatch, and use the cross-entropy loss function as the classification loss. Extensive experiments on 18 public projects from four datasets indicate that the proposed approach can build an effective prediction model for heterogeneous defect prediction (HDP) and outperforms the related competing approaches.
- Publication
- IEICE TRANSACTIONS on Information Vol.E102-D No.3 pp.537-549
- Publication Date
- 2019/03/01
- Publicized
- 2018/12/05
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2018EDP7289
- Type of Manuscript
- PAPER
- Category
- Software Engineering
Authors
Lina GONG
China University of Mining and Technology,Zaozhuang University
Shujuan JIANG
China University of Mining and Technology,Engineering Research Center of Mine Digitalization of Ministry of Education
Qiao YU
Jiangsu Normal University
Li JIANG
China University of Mining and Technology,Engineering Research Center of Mine Digitalization of Ministry of Education
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Lina GONG, Shujuan JIANG, Qiao YU, Li JIANG, "Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 3, pp. 537-549, March 2019, doi: 10.1587/transinf.2018EDP7289.
Abstract: Heterogeneous defect prediction (HDP) is to detect the largest number of defective software modules in one project by using historical data collected from other projects with different metrics. However, these data can not be directly used because of different metrics set among projects. Meanwhile, software data have more non-defective instances than defective instances which may cause a significant bias towards defective instances. To completely solve these two restrictions, we propose unsupervised deep domain adaptation approach to build a HDP model. Specifically, we firstly map the data of source and target projects into a unified metric representation (UMR). Then, we design a simple neural network (SNN) model to deal with the heterogeneous and class-imbalanced problems in software defect prediction (SDP). In particular, our model introduces the Maximum Mean Discrepancy (MMD) as the distance between the source and target data to reduce the distribution mismatch, and use the cross-entropy loss function as the classification loss. Extensive experiments on 18 public projects from four datasets indicate that the proposed approach can build an effective prediction model for heterogeneous defect prediction (HDP) and outperforms the related competing approaches.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7289/_p
Copy
@ARTICLE{e102-d_3_537,
author={Lina GONG, Shujuan JIANG, Qiao YU, Li JIANG, },
journal={IEICE TRANSACTIONS on Information},
title={Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction},
year={2019},
volume={E102-D},
number={3},
pages={537-549},
abstract={Heterogeneous defect prediction (HDP) is to detect the largest number of defective software modules in one project by using historical data collected from other projects with different metrics. However, these data can not be directly used because of different metrics set among projects. Meanwhile, software data have more non-defective instances than defective instances which may cause a significant bias towards defective instances. To completely solve these two restrictions, we propose unsupervised deep domain adaptation approach to build a HDP model. Specifically, we firstly map the data of source and target projects into a unified metric representation (UMR). Then, we design a simple neural network (SNN) model to deal with the heterogeneous and class-imbalanced problems in software defect prediction (SDP). In particular, our model introduces the Maximum Mean Discrepancy (MMD) as the distance between the source and target data to reduce the distribution mismatch, and use the cross-entropy loss function as the classification loss. Extensive experiments on 18 public projects from four datasets indicate that the proposed approach can build an effective prediction model for heterogeneous defect prediction (HDP) and outperforms the related competing approaches.},
keywords={},
doi={10.1587/transinf.2018EDP7289},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction
T2 - IEICE TRANSACTIONS on Information
SP - 537
EP - 549
AU - Lina GONG
AU - Shujuan JIANG
AU - Qiao YU
AU - Li JIANG
PY - 2019
DO - 10.1587/transinf.2018EDP7289
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2019
AB - Heterogeneous defect prediction (HDP) is to detect the largest number of defective software modules in one project by using historical data collected from other projects with different metrics. However, these data can not be directly used because of different metrics set among projects. Meanwhile, software data have more non-defective instances than defective instances which may cause a significant bias towards defective instances. To completely solve these two restrictions, we propose unsupervised deep domain adaptation approach to build a HDP model. Specifically, we firstly map the data of source and target projects into a unified metric representation (UMR). Then, we design a simple neural network (SNN) model to deal with the heterogeneous and class-imbalanced problems in software defect prediction (SDP). In particular, our model introduces the Maximum Mean Discrepancy (MMD) as the distance between the source and target data to reduce the distribution mismatch, and use the cross-entropy loss function as the classification loss. Extensive experiments on 18 public projects from four datasets indicate that the proposed approach can build an effective prediction model for heterogeneous defect prediction (HDP) and outperforms the related competing approaches.
ER -
English
