Idioma:

Defect Prediction With Semantics and Context Features of Codes Based on Graph Representation Learning

Xu, Jiaxi ; Wang, Fei ; Ai, Jun

IEEE transactions on reliability, 2021-06, Vol.70 (2), p.613-625 [Periódico revisado por pares]

New York: IEEE

Texto completo disponível

Citações Citado por

Enviar para

Título:
Defect Prediction With Semantics and Context Features of Codes Based on Graph Representation Learning
Autor: Xu, Jiaxi ; Wang, Fei ; Ai, Jun
Assuntos: Ablation ; Computer bugs ; Context ; Data mining ; Deep learning ; defect prediction ; Defects ; Graph neural networks ; graph representation learning ; Graph representations ; Graphical representations ; Machine learning ; Measurement ; Predictions ; Semantics ; Software ; software defect dataset ; Software development management ; software engineering ; Software reliability ; Software testing ; Syntactics ; Workflow
É parte de: IEEE transactions on reliability, 2021-06, Vol.70 (2), p.613-625
Descrição: To optimize the process of software testing and to improve software quality and reliability, many attempts have been made to develop more effective methods for predicting software defects. Previous work on defect prediction has used machine learning and artificial software metrics. Unfortunately, artificial metrics are unable to represent the features of syntactic, semantic, and context information of defective modules. In this article, therefore, we propose a practical approach for identifying software defect patterns via the combination of semantics and context information using abstract syntax tree representation learning. Graph neural networks are also leveraged to capture the latent defect information of defective subtrees, which are pruned based on a fix-inducing change. To validate the proposed approach for predicting defects, we define mining rules based on the GitHub workflow and collect 6052 defects from 307 projects. The experiments indicate that the proposed approach performs better than the state-of-the-art approach and five traditional machine learning baselines. An ablation study shows that the information about code concepts leads to a significant increase in accuracy.
Editor: New York: IEEE
Idioma: Inglês

Voltar para lista de resultados

Anterior Resultado 4 Avançar Ir para próxima página

Realização: Logos de Redes Sociais:

Defect Prediction With Semantics and Context Features of Codes Based on Graph Representation Learning

Xu, Jiaxi ; Wang, Fei ; Ai, Jun

New York: IEEE

Buscando em bases de dados remotas. Favor aguardar.