Transfer Defect Learning

Jaechang Nam, Sinno Jialin Pan, Sunghun Kim

2014 · 288 citations · 52 references

Concepts

Abstract

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 cross-project 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 exper-imental results for eight open-source projects show that TCA+ significantly improves cross-project prediction performance. Index Terms—cross-project defect prediction, transfer learn-ing, empirical software engineering I.

References

52