Graph Neural Network for Source Code Defect Prediction

Abstract

Predicting defective software modules before testing is a useful operation that ensures that the time and cost of software testing can be reduced. In recent years, several models have been proposed for this purpose, most of which are built using deep learning-based methods. However, most of these models do not take full advantage of a source code as they ignore its tree structure or they focus only on a small part of a code. To investigate whether and to what extent information from this structure can be beneficial in predicting defective source code, we developed an end-to-end model based on a convolutional graph neural network (GCNN) for defect prediction, whose architecture can be adapted to the analyzed software, so that projects of different sizes can be processed with the same level of detail. The model processes the information of the nodes and edges from the abstract syntax tree (AST) of the source code of a software module and classifies the module as defective or not defective based on this information. Experiments on open source projects written in Java have shown that the proposed model performs significantly better than traditional defect prediction models in terms of AUC and F-score. Based on the F-scores of the existing state-of-the-art models, the model has shown comparable predictive capabilities for the analyzed projects.INDEX TERMS Software defect prediction, deep learning, graph neural network.

Empirical Study: How Issue Classification Influences Software Defect Prediction

“…Many kinds of models have been used to tackle SDP. Researchers have proposed using supervised models [63], [64], [65], semi-supervised models [66], [67], unsupervised models [23], tasks specific models such as BugCache [22] and even approaching the problem as an anomaly detection problem [20], [21].…”

An in-Depth Analysis of the Software Features’ Impact on the Performance of Deep Learning-Based Software Defect Predictors

“…Very recently, Sikic et al [58] have proposed DP-GCNN, a SDP model based on a Convolutional Graph Neural Network (GCNN), which is fed with AST data. The neural network architecture employed is specifically tailored for graph data.As experimental data, the authors have considered 7 SDP data sets from the Promise repository.…”

“…Traditional metrics were combined with features learnt from AST using a Convolutional Neural Network (CNN) by Li et al [75]. Šikić et al [76] used a graph convolutional neural network (GCNN) for processing the information of the nodes and edges from the AST of the source code for classifying the module as being defective or non-defective. Doc2Vec [77] and LSI [78] models may also be used for unsupervisedly learning conceptual-based features from the source code.…”

“…The next three feature sets, labeled as AST+SM, AST+PMD and AST+D'Ambros are obtained by fusing the AST-based features and the SM, PMD and D'Ambros features sets, respectively. We decided to use the AST-based features in all these combinations since the literature reveals various approaches [18], [75], [76] in which deep learning models are used to learn relevant features starting from the ASTs of the source code. 9.-10.…”

Gaussian kernelized feature selection and improved multilayer perceptive deep learning classifier for software fault prediction

“…Semantic feature learning via defect prediction via stress-based forming limit diagrams (DP-SFLDS) method was developed in [1] to extracting the semantic and structural information using bi-directional long short-term memory (BiLSTM) based neural network. But the complexity of the algorithm was not reduced to and it failed to provide accurate predictions.…”