Cross version defect prediction with representative data via sparse subset selection

Zhou, Xu; Li, Shuai; Tang, Yutian; Luo, Xiapu; Zhang, Tao; Liu, Jin; Xu, Jun

doi:10.1145/3196321.3196331

Cited by 31 publications

(35 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bin et al [4] investigated more strategies for instance selection and surprisingly found performing instance selection is not necessary. Xu et al [86] proposed dissimilarity-based sparse feature selection method. Ma et al [49] proposed Transfer Naive Bayes (TNB) method.…”

Section: Supervised Homogeneous Cpdp Methodsmentioning

confidence: 99%

Revisiting Heterogeneous Defect Prediction: How Far Are We?

Chen,

Mu,

et al. 2019

Preprint

View full text Add to dashboard Cite

Cross-project defect prediction (CPDP) is applicable to the scenarios when the target projects are new projects or these projects only have a few training data. Most of the previous studies on CPDP tried to utilize the training data from other projects (i.e., the source projects) and then resorted to transfer learning to alleviate the data distribution difference between different projects. However, different metrics may be used by practitioners to measure the extracted program modules from different projects and performing CPDP across these projects with heterogeneous metrics is more challenging. This issue is named as heterogeneous defect prediction (HDP). Until now, researchers have proposed several novel HDP methods with promising performance. Recently, unsupervised methods have been widely studies in CPDP and show the competitive performance. Moreover, this kind of methods can be easily compared with HDP methods. To the best of our knowledge, whether HDP methods can perform significantly better than these unsupervised methods has not yet been thoroughly investigated. In this article, we perform a replication study to have a holistic look in this issue. In particular, we compare stateof-the-art five HDP methods with state-of-the-art five unsupervised methods. Final results surprisingly show that these HDP methods do not perform sig-

show abstract

Section: Supervised Homogeneous Cpdp Methodsmentioning

confidence: 99%

Revisiting Heterogeneous Defect Prediction: How Far Are We?

Chen,

Mu,

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Cross-version context is where the training data to predict the defects in the current version of a project is comprised of data from its prior versions [98,99]. For instance, in the Cross-version context, one uses versions V 1 ,V 2 ,.…”

Section: Sdp Contextsmentioning

confidence: 99%

Revisiting the Impact of Dependency Network Metrics on Software Defect Prediction

Gong,

Rajbahadur,

Hassan

et al. 2022

Preprint

View full text Add to dashboard Cite

Software dependency network metrics extracted from the dependency graph of the software modules by the application of Social Network Analysis (SNA metrics) have been shown to improve the performance of the Software Defect prediction (SDP) models. However, the relative effectiveness of these SNA metrics over code metrics in improving the performance of the SDP models has been widely debated with no clear consensus. Furthermore, some of the common SDP scenarios like predicting the number of defects in a module (Defect-count) in Cross-version and Cross-project SDP contexts remain unexplored. Such lack of clear directive on the effectiveness of SNA metrics when compared to the widely used code metrics prevents us from potentially building better performing SDP models. Therefore, through a case study of 9 open source software projects across 30 versions, we study the relative effectiveness of SNA metrics when compared to code metrics across 3 commonly used SDP contexts (Within-project, Cross-version and Crossproject) and scenarios (Defect-count, Defect-classification (classifying if a module is defective) and Effort-aware (ranking the defective modules w.r.t to the involved effort)). We find the SNA metrics by themselves or along with code metrics improve the performance of SDP models over just using code metrics on 5 out of the 9 studied SDP scenarios (three SDP scenarios across three SDP contexts). However, we note that in some cases the improvements afforded by considering SNA metrics over or alongside code metrics might only be marginal, whereas in other cases the improvements could be potentially large. Based on these findings we suggest that the future work should: consider SNA metrics alongside code metrics in their SDP models; as well as consider Ego metrics and Global metrics, the two different types of the SNA metrics separately when training SDP models as they behave differently.

show abstract

“…Bin et al considered more strategies for instance selection and surprisingly found there is no need to perform instance selection. Xu et al leveraged dissimilarity‐based sparse subset selection method. Ma et al proposed the transfer naive Bayes (TNB) method, which can assign weights for the instances in the source project.…”

Section: Background and Related Workmentioning

confidence: 99%

Do different cross‐project defect prediction methods identify the same defective modules?

Chen

Qu³

et al. 2019

J Software Evolu Process

View full text Add to dashboard Cite

Cross‐project defect prediction (CPDP) is needed when the target projects are new projects or the projects have less training data, since these projects do not have sufficient historical data to build high‐quality prediction models. The researchers have proposed many CPDP methods, and previous studies have conducted extensive comparisons on the performance of different CPDP methods. However, to the best of our knowledge, it remains unclear whether different CPDP methods can identify the same defective modules, and this issue has not been thoroughly explored. In this article, we select 12 state‐of‐the‐art CPDP methods, including eight supervised methods and four unsupervised methods. We first compare the performance of these methods in the same experiment settings on five widely used datasets (ie, NASA, SOFTLAB, PROMISE, AEEEM, and ReLink) and rank these methods via the Scott‐Knott test. Final results confirm the competitiveness of unsupervised methods. Then we perform diversity analysis on defective modules for these methods by using the McNemar test. Empirical results verify that different CPDP methods may lead to difference in the modules predicted as defective, especially when the comparison is performed between the supervised methods and unsupervised methods. Finally, we also find there exist a certain number of defective modules, which cannot be correctly identified by any of the CPDP methods or can be correctly identified by only one CPDP method. These findings can be utilized to design more effective methods to further improve the performance of CPDP.

show abstract

Cross version defect prediction with representative data via sparse subset selection

Cited by 31 publications

References 59 publications

Revisiting Heterogeneous Defect Prediction: How Far Are We?

Revisiting Heterogeneous Defect Prediction: How Far Are We?

Revisiting the Impact of Dependency Network Metrics on Software Defect Prediction

Do different cross‐project defect prediction methods identify the same defective modules?

Contact Info

Product

Resources

About