Shaojian Qiu

Software defect prediction technology aids the reliability assurance team in identifying defect-prone code and assists the team in reasonably allocating limited testing resources. Recently, researchers assumed that the topological associations among code fragments could be harnessed to construct defect prediction models. Nevertheless, existing graph-based methods only concentrate on features of single-view association, which fail to fully capture the rich information hidden in the code. In addition, software defects may involve multiple code fragments simultaneously, but traditional binary graph structures are insufficient for representing these multivariate associations. To address these two challenges, this article proposes a multiview hypergraph representation learning approach (MVHR-DP) to amplify the potency of code features in defect prediction. MVHR-DP initiates by creating hypergraph structures for each code view, which are then amalgamated into a comprehensive fusion hypergraph. Following this, a hypergraph neural network is established to extract code features from multiple views and intricate associations, thereby enhancing the comprehensiveness of representation in the modeling data. Empirical study shows that the prediction model utilizing features generated by MVHR-DP exhibits superior area under the curve (AUC), F-measure, and matthews correlation coefficient (MCC) results compared to baseline approaches across within-project, cross-version, and cross-project prediction tasks.

Defects in software may result in system crashes, sluggish performance, or even deadlock, leading to the depletion of valuable resources. Implementing defect prediction can assist quality assurance teams in identifying potential software issues and rationalizing the allocation of testing resources, thereby decreasing the elimination of resources and enhancing software sustainability. Researchers have recently incorporated deep learning into defect prediction, extracting structural-semantic features from codes' abstract syntax trees (ASTs). However, inappropriate node granularity in ASTs may adversely impact the effectiveness of the extracted features. In addition, converting AST nodes into integer vectors may lead to the loss of structure information, resulting in poor model predictive capability. This paper proposes a tree-based encoding method with hybrid granularity for defect prediction to address these challenges. Specifically, five granularity selection schemes are extended to generate various ASTs from codes. Subsequently, a tree-based continuous bag-of-words model is utilized to map nodes of ASTs into numeric vector representations that conform to the tree-like structure of codes. The matrices converted from ASTs are then fed into a convolutional neural network to extract program features automatically. Experiments involving 24 versions of open-source projects demonstrate that our method can improve the effectiveness of extracted features in defect prediction tasks.

Cross-project defect prediction (CPDP) is a feasible way to perform software defect prediction (SDP) when lacking historical data. Recent CPDP approaches have employed deep learning techniques to better exploit the information from the program's abstract syntax trees (ASTs). However, the granularity of the AST nodes and the data distribution difference between projects may have negative impacts on the prediction performance, which many CPDP studies didn't take into consideration. To handle these issues, this paper explores a better AST node granularity and proposes a CPDP framework based on multi-kernel transfer convolutional neural networks. Specifically, for AST node granularity, we explore the difference of three AST node granularities and then compare the prediction performance of each granularity on several prediction models. For the CPDP framework, we first parse the program source code into ASTs and then encode the AST nodes into numerical vectors using the embedding technique. Secondly, to mine transferable semantic features, the encoded ASTs are fed into a convolutional neural network, in which a multi-kernel matching layer is added to minimize the data distribution divergence between the source and target project. Finally, to make use of the information from the handcrafted features, the semantic features mined from the AST are joint with handcrafted features to form the joint features for CPDP. We evaluate our approach on 110 CPDP tasks formed by 11 open-source projects and results show that the proposed CPDP method outperforms most deep learning-based approaches.

Machine-learning-based software defect prediction (SDP) methods are receiving great attention from the researchers of intelligent software engineering. Most existing SDP methods are performed under a within-project setting. However, there usually is little to no within-project training data to learn an available supervised prediction model for a new SDP task. Therefore, cross-project defect prediction (CPDP), which uses labeled data of source projects to learn a defect predictor for a target project, was proposed as a practical SDP solution. In real CPDP tasks, the class imbalance problem is ubiquitous and has a great impact on performance of the CPDP models. Unlike previous studies that focus on subsampling and individual methods, this study investigated 15 imbalanced learning methods for CPDP tasks, especially for assessing the effectiveness of imbalanced ensemble learning (IEL) methods. We evaluated the 15 methods by extensive experiments on 31 open-source projects derived from five datasets. Through analyzing a total of 37504 results, we found that in most cases, the IEL method that combined under-sampling and bagging approaches will be more effective than the other investigated methods.

In the last few years, with the development of deep learning theory, researchers have tried to introduce the method of artificial intelligence into the field of software defect prediction (SDP) to improve its prediction effect. To be fed into the neural network, the sample codes are represented as an abstract syntax tree (AST), and the AST is encoded as real numbers. However, in most cross-project defect prediction (CPDP) task, the method for converting the AST into a real number cannot effectively estimate the semantic distance between the ASTs, resulting in a significant reduction in training effects. To solve that problem, we present a new encoding framework, tree-based-embedding (TBE), to convert AST into real vectors and make the semantic gap between the ASTs measurable. To estimate the effect of this encoding method, we promise a tree-based-embedding convolutional neural network with transferable hybrid feature learning (TBCNN-THFL) to perform the CPDP tasks. TBCNN-THFL is fed data encoded with TBE method for learning the transferable joint features between different projects; meanwhile, TBCNN-THFL introduces a transfer component analysis algorithm. Furthermore, the model combines the handcrafted and deep-learning-generated features and then feeds them into the classifier to train a defect prediction model. A sufficient number of experiments demonstrate that TBCNN-THFL is superior to referential models on 72 pairs of CPDP tasks formed by 9 open-source projects.

Cross-project defect prediction (CPDP) is a practical solution that allows software defect prediction (SDP) to be used earlier in the software lifecycle. With the CPDP technique, the software defect predictor trained by labeled data of mature projects can be applied for the prediction task of a new project. Most previous CPDP approaches ignored the semantic information in the source code, and existing semantic-feature-based SDP methods do not take into account the data distribution divergence between projects. These limitations may weaken defect prediction performance. To solve these problems, we propose a novel approach, the transfer convolutional neural network (TCNN), to mine the transferable semantic (deep-learning (DL)-generated) features for CPDP tasks. Specifically, our approach first parses the source file into integer vectors as the network inputs. Next, to obtain the TCNN model, a matching layer is added into convolutional neural network where the hidden representations of the source and target project-specific data are embedded into a reproducing kernel Hilbert space for distribution matching. By simultaneously minimizing classification error and distribution divergence between projects, the constructed TCNN could extract the transferable DL-generated features. Finally, without losing the information contained in handcrafted features, we combine them with transferable DL-generated features to form the joint features for CPDP performing. Experiments based on 10 benchmark projects (with 90 pairs of CPDP tasks) showed that the proposed TCNN method is superior to the reference methods.