Journal Article10.1109/ACCESS.2022.3144598
Graph Neural Network for Source Code Defect Prediction
Lucija Sikic,Adrian Satja Kurdija,Klemo Vladimir,Marin Silic +3 more
- Vol. PP, pp 1-1
TL;DR: 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.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Semantic and traditional feature fusion for software defect prediction using hybrid deep learning model
Ahmed Abdu,Zhengjun Zhai,Hakim A. Abdo,Redhwan Algabri,Mohammed A. Al‐masni,Mannan Saeed Muhammad,Yeong Hyeon Gu +6 more
TL;DR: Experimental results indicate that CNN-MLP can significantly enhance defect prediction performance, and CNN-MLP’s improvements outperform existing methods in non-effort-aware and effort-aware cases.
8
Software Defect Prediction using Machine Learning
Sonia Setia,Kiran Kumar Ravulakollu,Kimmi Verma,Setu Garg,Sunil Kumar Mishra,Bhagwati Sharan +5 more
- 28 Feb 2024
TL;DR: This research work presents numerous algorithms, namely Gaussian naive bayes (GNB), Bernoulli NB, random forest (RF) and multi-layer perceptron (MLP), for predicting the software defect and focuses on developing an ensemble algorithm to enhance the efficacy of predicting the defects.
3
Cognitive Complexity and Graph Convolutional Approach Over Control Flow Graph for Software Defect Prediction
TL;DR: An effort has been made to categorize the Control Flow Graphs (CFGs) nodes according to their node features, and the proposed models outperformed state-of-the-art methods such as Nave Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF) in all evaluation criteria.
3
VulScan: A Vulnerability Detection Model Based on Deep Learning
Liu M,Yiwen Zhang +1 more
- 01 Jun 2023
TL;DR: VulScan is a deep learning model for vulnerability detection in source code that utilizes GCN and BiLSTM to capture structural and sequential information. It achieves superior performance compared to baseline techniques.
2
Deep Learning Based Continuous Integration and Continuous Delivery Software Defect Prediction with Effective Optimization Strategy
Ashish Sharma
TL;DR: A deep learning-based CI/CD software defect prediction technique is proposed, utilizing M-SMOTE, F-BERT, and Bi-CGRU models with HLR optimization to improve efficiency, achieving 95.32% accuracy, 93.3% recall, and 94.98% Matthews correlation coefficient.
1
References
Towards identifying software project clusters with regard to defect prediction
Marian Jureczko,Lech Madeyski +1 more
- 12 Sep 2010
TL;DR: The results of this work makes next step towards defining formal methods of reuse defect prediction models by identifying groups of projects within which the same defect prediction model may be used.
Predicting defect-prone software modules using support vector machines
Karim O. Elish,Mahmoud O. Elish +1 more
TL;DR: Evaluating the capability of SVM in predicting defect-prone software modules and comparing its prediction performance against eight statistical and machine learning models in the context of four NASA datasets indicates that the prediction performance is generally better than or at least is competitive against the compared models.
581
An Empirical Comparison of Model Validation Techniques for Defect Prediction Models
TL;DR: It is found that single-repetition holdout validation tends to produce estimates with 46-229 percent more bias and 53-863 percent more variance than the top-ranked model validation techniques, and out-of-sample bootstrap validation yields the best balance between the bias and variance.
580
Defect prediction from static code features: current results, limitations, new approaches
Tim Menzies,Zach Milton,Burak Turhan,Bojan Cukic,Yue Jiang,Ayse Bener +5 more
- 01 Dec 2010
TL;DR: It is hypothesized that the limits of the standard learning goal of maximizing area under the curve (AUC) of the probability of false alarms and probability of detection “AUC(pd, pf)” are reached, and certain widely used learners perform much worse than simple manual methods.
Software fault prediction metrics
TL;DR: Object-oriented and process metrics have been reported to be more successful in finding faults compared to traditional size and complexity metrics and seem to be better at predicting post-release faults than any static code metrics.
482