He Qing
ABSTRACT
Cross-project defect prediction is taken as an effective means of predicting software defects when the data shortage exists in the early phase of software development. Unfortunately, the precision of cross-project defect prediction is usually poor, largely because of the differences between the reference and the target projects. Having realized the project differences, this paper proposes CPDP, a feature-based transfer learning approach to cross-project defect prediction. The core insight of CPDP is to (1) filter and transfer highly-correlated data based on data samples in the target projects, and (2) evaluate and choose learning schemas for transferring data sets. Models are then built for predicting defects in the target projects. We have also conducted an evaluation of the proposed approach on PROMISE datasets. The evaluation results show that, the proposed approach adapts to cross-project defect prediction in that f-measure of 81.8% of projects can get improved, and AUC of 54.5% projects improved. It also achieves similar f-measure and AUC as some inner-project defect prediction approaches.
- Akiyama F. An example of software system debugging. In: Proc. of the Int'l Federation of Information Proc. Societies Congress. New York: Springer Science and Business Media, 1971. 353--359.Google Scholar
- Turhan B, Menzies T, Bener A, et al. On the relative value of cross-company and within-company data for defect prediction. Empirical Software Engineering, 2009, 14(5): 540--578. Google ScholarDigital Library
- Zimmermann T, Nagappan N, Gall H, et al. Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In: Proc. of the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on the foundations of software engineering, NY, USA, 2009, 91--100. Google ScholarDigital Library
- Nagappan N, Ball T, Zeller, A. Mining metrics to predict component failures. In: Proc. of the 28th international conference on Software engineering, NY, USA, 2006, 452--461. Google ScholarDigital Library
- Turhan B, Menzies T, Bener A B, et al. On the relative value of cross-company and within-company data for defect prediction. Empirical Software Engineering, 2009, 14(5): 540--578. Google ScholarDigital Library
- Zhuang FZ, He Q, Shi ZZ. Survey on transfer learning research. Journal of Software, 2015, 26(1): 26--39. (in Chinese with English abstract).Google Scholar
- Wang Q, Wu SJ, Li MS. Software Defect Prediction. Journal of Software, 2008, 19(7): 1565--1580. (in Chinese with English abstract).Google ScholarCross Ref
- Briand L C, Melo W L, Wust J. Assessing the applicability of faultproneness models across object-oriented software projects. IEEE Transactions on Software Engineering, 2002, 28(7): 706--720. Google ScholarDigital Library
- Cruz A, Ochimizu K. Towards logistic regression models for predicting fault-prone code across software projects. In: Proc. of Empirical Software Engineering and Measurement, Lake Buena Vista, FL, 2009, 460--463. Google ScholarDigital Library
- Nam J, Pan S J, Kim S. Transfer defect learning. In: Proc. of International Conference on Software Engineering, San Francisco, CA, 2013, 382--391. Google ScholarDigital Library
- Pan S J, Tsang I W, Kwok J T, et al. Domain Adaptation via Transfer Component Analysis. IEEE Transactions on Neural Networks, 2010, 22(2): 199--210. Google ScholarDigital Library
- Peters F, Menzies T, Marcus A. Better cross company defect prediction. In: Proc. of the Tenth International Workshop on Mining Software Repositories, San Francisco, CA, 2013, 409--418. Google ScholarDigital Library
- Tosun A, Bener A B, Kale R. AI-Based Software Defect Predictors: Applications and Benefits in a Case Study. IAAI, 2011, 32(2): 57--68.Google Scholar
- Fayola Peters, Tim Menzies, Liang Gong, Hongyu Zhang. Balancing Privacy and Utility in Cross-Company Defect Prediction. IEEE Trans. Software Eng. 39(8): 1054--106. Google ScholarDigital Library
- Jureczko M, Madeyski L. Towards identifying software project clusters with regard to defect prediction. In: Proc. of the 6th International Conference on Predictive Models in Software Engineering, 2012, 9, ACM. Google ScholarDigital Library
- Zhang F, Mockus A, Keivanloo I, et al. Towards Building a Universal Defect Prediction Model. In: Proc. of the 11th Working Conference on Mining Software Repositories, 2014, 182--191. Google ScholarDigital Library
- Ming Li, Hongyu Zhang, Rongxin Wu, Zhi-Hua Zhou. Sample-based software defect prediction with active and semi-supervised learning. Automated Software Engineering, 2012, 19(2): 201--230. Google ScholarDigital Library
- Liu Y, Khoshgoftaar T M, Seliya N. Evolutionary optimization of software quality modeling with multiple repositories. IEEE Transactions on Software Engineering, 2010, 36(6): 852--864. Google ScholarDigital Library
- Nam J, Pan S J, Kim S. Transfer defect learning. In: Proc. of the 2013 International Conference on Software Engineering, San Francisco, CA, 2013, 382--391. Google ScholarDigital Library
- Wenyuan Dai, Qiang Yang, Gui-Rong Xue, Yong Yu. Boosting for transfer learning. In: Proc. of ICML 2007: 193--200 Google ScholarDigital Library
- Wenyuan Dai, Yuqiang Chen, Gui-Rong Xue, Qiang Yang, Yong Yu. Translated Learning: Transfer Learning across Different Feature Spaces. NIPS 2008: 353--360 Google ScholarDigital Library
- Wenyuan Dai, Ou Jin, Gui-Rong Xue, Qiang Yang, Yong Yu. EigenTransfer: a unified framework for transfer learning. ICML 2009: 193--200 Google ScholarDigital Library
- Dai WY. Instance-based and Feature-based Transfer Learning {MS. Thesis}. Shanghai Jiao Tong University, 2008 (in Chinese with English abstract).Google Scholar
- Peters F, Menzies T, Gong L, et al. Balancing privacy and utility in cross-company defect prediction. IEEE Transactions on Software Engineering, 2013, 33(9): 637--640. Google ScholarDigital Library
- Scholkopf B, Smola A, Muller K R. Kernel Principal Component Analysis. Lecture Notes in Computer Science, 1997, 1327: 583--588. Google ScholarDigital Library
Index Terms
- Cross-Project Software Defect Prediction Using Feature-Based Transfer Learning
Recommendations
Understanding the automated parameter optimization on transfer learning for cross-project defect prediction: an empirical study
ICSE '20: Proceedings of the ACM/IEEE 42nd International Conference on Software EngineeringData-driven defect prediction has become increasingly important in software engineering process. Since it is not uncommon that data from a software project is insufficient for training a reliable defect prediction model, transfer learning that borrows ...
Cross-project smell-based defect prediction
AbstractDefect prediction is a technique introduced to optimize the testing phase of the software development pipeline by predicting which components in the software may contain defects. Its methodology trains a classifier with data regarding a set of ...
A transfer cost-sensitive boosting approach for cross-project defect prediction
Software defect prediction has been regarded as one of the crucial tasks to improve software quality by effectively allocating valuable resources to fault-prone modules. It is necessary to have a sufficient set of historical data for building a ...
Comments