Joint distribution matching model for distribution–adaptation‐based cross‐project defect prediction. Issue 5 (1st October 2019)

• Record Type: Journal Article
• Authors: Qiu, Shaojian; Lu, Lu; Jiang, Siyu
• Is Part Of: IET software. Volume 13:Issue 5(2019)
• Page Start: 393
• Page End: 402
• Publication Date: 2019-10-01
• Subjects: pattern classification -- learning (artificial intelligence) -- vectors; joint distribution matching model -- classification methods -- software defect -- within-project setting -- labelled data -- effective prediction model -- software lifecycle -- defect predictor -- target project -- source project -- instances selection -- classifiers adjustment -- JDM -- joint distribution divergence -- CPDP performance -- adaptive weight vector -- marginal distribution discrepancy -- conditional distribution discrepancy -- distribution–adaptation-based methods -- open-source projects -- cross-project defect prediction; Computer software -- Periodicals; Software engineering -- Periodicals; 005.1
• DOI: 10.1049/iet-sen.2018.5131
• Languages: English
• ISSNs: 1751-8806

Abstract

Abstract : Using classification methods to predict software defect is receiving a great deal of attention and most of the existing studies primarily conduct prediction under the within‐project setting. However, there usually had no or very limited labelled data to train an effective prediction model at an early phase of the software lifecycle. Thus, cross‐project defect prediction (CPDP) is proposed as an alternative solution, which is learning a defect predictor for a target project by using labelled data from a source project. Differing from previous CPDP methods that mainly apply instances selection and classifiers adjustment to improve the performance, in this study, the authors put forward a novel distribution–adaptation‐based CPDP approach, joint distribution matching (JDM). Specifically, JDM aims to minimise the joint distribution divergence between the source and target project to improve the CPDP performance. By constructing an adaptive weight vector for the instances of the source project, JDM can be effective and robust at reducing marginal distribution discrepancy and conditional distribution discrepancy simultaneously. Extensive experiments verify that JDM can outperform related distribution–adaptation‐based methods on 15 open‐source projects that are derived from two types of repositories.