Transfer defect learning

Abstract

Many software defect prediction approaches have been proposed and most are effective in within-project prediction settings. However, for new projects or projects with limited training data, it is desirable to learn a prediction model by using sufficient training data from existing source projects and then apply the model to some target projects (cross-project defect prediction). Unfortunately, the performance of crossproject defect prediction is generally poor, largely because of feature distribution differences between the source and target projects.In this paper, we apply a state-of-the-art transfer learning approach, TCA, to make feature distributions in source and target projects similar. In addition, we propose a novel transfer defect learning approach, TCA+, by extending TCA. Our experimental results for eight open-source projects show that TCA+ significantly improves cross-project prediction performance.Index Terms-cross-project defect prediction, transfer learning, empirical software engineering I. INTRODUCTION Recently, numerous effective software defect prediction approaches have been proposed and received a tremendous amount of attention [1], [2], [3], [4], [5]. Most approaches employ machine learning classifiers to build a prediction model from data sets mined from software repositories, and the model is used to identify software defects. However, most approaches are evaluated in within-project settings, i.e., a prediction model is built from a part of a project and the model is evaluated with the remainder of the project by 10-fold cross validation [2], [6], [7], [8] and/or random instance splits [5], [9], [10].In practice, cross-project defect prediction is necessary. New projects often do not have enough defect data to build a prediction model. This cold-start is a well-known problem for recommender systems [11] and can be addressed by using cross-project defect prediction to build a prediction model using data from other projects. The model is then applied to new projects.However, cross-project defect prediction often yields poor performance. Zimmermann et al.[12] evaluated cross-project defect prediction performance based on data from 12 projects (622 combinations). They found that only 21 pairs yielded reasonable prediction performance.One of the main reasons for the poor cross-project prediction performance is the difference between the data distributions of source and target projects. Most machine learning classifiers are designed under the assumption that training and

Kernel CCA Based Transfer Learning for Software Defect Prediction

“…In order to investigate the performance of our algorithm, we compare it with NN-filter [7], TNB [12], TCA+ [13], CCA+ [16] (Gaussian RBF kernel γ = 10, c = 1000). For each data set, we perform 5-fold cross validation.…”

“…Nam et al [13] extended the Transfer Component Copyright c 2017 The Institute of Electronics, Information and Communication Engineers Analysis (TCA) to improve cross-project prediction performance. Chen et al [14] proposed a novel algorithm based on double boosting to improve the performance of crosscompany defects prediction by reducing negative samples in cross-company data.…”

Combing Data Filter and Data Sampling for Cross-Company Defect Prediction: An Empricial Study

“…The second mainstream way is to design effective defect predictor based on transfer learning techniques (e.g., [7,10,15,16,17,18,19]). For instance, Ma et al [15] proposed Transfer Naï ve Bayes (TNB) model.…”

Self-learning Change-prone Class Prediction

“…The cross project concept is introduced by Briand et al [21]. It has been widely used in defect prediction [14,[22][23][24][25]. In change-prone class prediction, there are also a few studies which have investigated the cross-project change prediction recently.…”

“…The cross project technique is motivated by the similar techniques in defect prediction [14,15]. It enables change-prone class prediction on projects with limited labeled dataset by learning from other projects.…”