Semi-supervised Heterogeneous Defect Prediction with Open-source Projects on GitHub

The heterogeneous defect prediction (HDP) technique can predict defects in a target company using heterogeneous metric data from external company, which has received substantial research attention. However, existing HDP methods assume that source data is labeled but labeling data is expensive. Semi-supervised defect prediction technique can perform defect prediction with few labeled data. In this paper, we investigate a new problem — semi-supervised HDP (SHDP). To solve this problem, we propose a new approach named cost-sensitive kernel semi-supervised correlation analysis (CKSCA) as a solution of SHDP problem. It introduces unified metric representation and canonical correlation analysis to make the data distributions of different company projects more similar. CKSCA also designs a cost-sensitive kernel semi-supervised discriminant analysis mechanism to utilize the limited labeled data and sufficient real-life unlabeled data from different companies. Besides we collect lots of open-source projects from GitHub website to construct a new large-scale unlabeled dataset called GITHUB dataset. It contains 26,407 modules and is greater than each public project dataset. It has been public online and can be extended continuously. Experiments on the GITHUB dataset and other public datasets indicate that unlabeled GITHUB data can help prediction model improve prediction performance, and CKSCA is effective and efficient for solving SHDP problem.

Heterogeneous Defect Prediction Based on Transfer Learning to Handle Extreme Imbalance

Software systems are now ubiquitous and are used every day for automation purposes in personal and enterprise applications; they are also essential to many safety-critical and mission-critical systems, e.g., air traffic control systems, autonomous cars, and Supervisory Control And Data Acquisition (SCADA) systems. With the availability of massive storage capabilities, high speed Internet, and the advent of Internet of Things devices, modern software systems are growing in both size and complexity. Maintaining a high quality of such complex systems while manually keeping the error rate at a minimum is a challenge. This paper proposed a heterogeneous defect prediction method considering class extreme imbalance problem in real software datasets. In the first stage, Sampling with the Majority method (SWIM) based on Mahalanobis Distance is used to balance the dataset to reduce the influence of minority samples in defect data. Due to the negative impact of uncorrelated features on the classification algorithm, the second stage uses ensemble learning and joint similarity measurement to select the most relevant and representative features between the source project and the target project. The third phase realizes the transfer learning from the source project to the target project in the Grassmann manifold space. Our experiments, conducted using nine projects of three public domain software defect libraries and compared with four existing advanced methods to verify the effectiveness of the proposed method in this paper. The experimental results indicate that the proposed method is more accurate in terms of Area under curve (AUC).