IEICE TRANSACTIONS on Information
A Data Augmentation Method for Fault Localization with Fault Propagation Context and VAE
Summary :
With the growing complexity and scale of software, detecting and repairing errant behaviors at an early stage are critical to reduce the cost of software development. In the practice of fault localization, a typical process usually includes three steps: execution of input domain test cases, construction of model domain test vectors and suspiciousness evaluation. The effectiveness of model domain test vectors is significant for locating the faulty code. However, test vectors with failing labels usually account for a small portion, which inevitably degrades the effectiveness of fault localization. In this paper, we propose a data augmentation method PVaug by using fault propagation context and variational autoencoder (VAE). Our empirical results on 14 programs illustrate that PVaug has promoted the effectiveness of fault localization.
- Publication
- IEICE TRANSACTIONS on Information Vol.E107-D No.2 pp.234-238
- Publication Date
- 2024/02/01
- Publicized
- 2023/10/25
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2023EDL8052
- Type of Manuscript
- LETTER
- Category
- Software Engineering
Authors
Zhuo ZHANG
Tianjin University
Donghui LI
Tianjin University
Lei XIA
No.83 Army Joint and Truma Disease Treatment Centre of PLA
Ya LI
Shanghai Jiaotong University
Xiankai MENG
Polytechnic University
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
Zhuo ZHANG, Donghui LI, Lei XIA, Ya LI, Xiankai MENG, "A Data Augmentation Method for Fault Localization with Fault Propagation Context and VAE" in IEICE TRANSACTIONS on Information,
vol. E107-D, no. 2, pp. 234-238, February 2024, doi: 10.1587/transinf.2023EDL8052.
Abstract: With the growing complexity and scale of software, detecting and repairing errant behaviors at an early stage are critical to reduce the cost of software development. In the practice of fault localization, a typical process usually includes three steps: execution of input domain test cases, construction of model domain test vectors and suspiciousness evaluation. The effectiveness of model domain test vectors is significant for locating the faulty code. However, test vectors with failing labels usually account for a small portion, which inevitably degrades the effectiveness of fault localization. In this paper, we propose a data augmentation method PVaug by using fault propagation context and variational autoencoder (VAE). Our empirical results on 14 programs illustrate that PVaug has promoted the effectiveness of fault localization.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDL8052/_p
Copy
@ARTICLE{e107-d_2_234,
author={Zhuo ZHANG, Donghui LI, Lei XIA, Ya LI, Xiankai MENG, },
journal={IEICE TRANSACTIONS on Information},
title={A Data Augmentation Method for Fault Localization with Fault Propagation Context and VAE},
year={2024},
volume={E107-D},
number={2},
pages={234-238},
abstract={With the growing complexity and scale of software, detecting and repairing errant behaviors at an early stage are critical to reduce the cost of software development. In the practice of fault localization, a typical process usually includes three steps: execution of input domain test cases, construction of model domain test vectors and suspiciousness evaluation. The effectiveness of model domain test vectors is significant for locating the faulty code. However, test vectors with failing labels usually account for a small portion, which inevitably degrades the effectiveness of fault localization. In this paper, we propose a data augmentation method PVaug by using fault propagation context and variational autoencoder (VAE). Our empirical results on 14 programs illustrate that PVaug has promoted the effectiveness of fault localization.},
keywords={},
doi={10.1587/transinf.2023EDL8052},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - A Data Augmentation Method for Fault Localization with Fault Propagation Context and VAE
T2 - IEICE TRANSACTIONS on Information
SP - 234
EP - 238
AU - Zhuo ZHANG
AU - Donghui LI
AU - Lei XIA
AU - Ya LI
AU - Xiankai MENG
PY - 2024
DO - 10.1587/transinf.2023EDL8052
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E107-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2024
AB - With the growing complexity and scale of software, detecting and repairing errant behaviors at an early stage are critical to reduce the cost of software development. In the practice of fault localization, a typical process usually includes three steps: execution of input domain test cases, construction of model domain test vectors and suspiciousness evaluation. The effectiveness of model domain test vectors is significant for locating the faulty code. However, test vectors with failing labels usually account for a small portion, which inevitably degrades the effectiveness of fault localization. In this paper, we propose a data augmentation method PVaug by using fault propagation context and variational autoencoder (VAE). Our empirical results on 14 programs illustrate that PVaug has promoted the effectiveness of fault localization.
ER -
English
