Learning Graph Representation of Bug Reports to Triage Bugs using Graph Convolution Network

Zaidi, Syed Farhan Alam; Lee, Chan-Gun

doi:10.1109/icoin50884.2021.9333902

Cited by 14 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN employed multiple convolutional kernels to extract diversified features, and their technique demonstrated state-of-the-art performance. Recently, a heterogeneous graph-based bug triage method [44] that uses a graph CNN was designed to create heterogeneous graphs from triage history. This method is quicker than the CNN and RNN methods and revealed results comparable to the existing methods.…”

Section: Conventional Machine Learning-based Bug Triagementioning

confidence: 99%

Toward an Effective Bug Triage System Using Transformers to Add New Developers

2022

Self Cite

View full text Add to dashboard Cite

As defects become more widespread in software development and advancement, bug triaging has become imperative for software testing and maintenance. The bug triage process assigns an appropriate developer to a bug report. Many automated and semiautomated systems have been proposed in the last decade, and some recent techniques have provided direction for developing an effective triage system. However, these techniques still require improvement. Another open challenge related to this problem is adding new developers to the existing triage system, which is challenging because the developers have no listed triage history. This paper proposes a transformer-based bug triage system that uses bidirectional encoder representation from transformers (BERT) for word representation. The proposed model can add a new developer to the existing system without building a training model from scratch. To add new developers, we assumed that new developers had a triage history created by a manual triager or human triage manager after learning their skills from the existing developer history. Then, the existing model was fine-tuned to add new developers using the manual triage history. Experiments were conducted using datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was used as a criterion for assessment. The experimental outcome suggests that the proposed triage system is better than other word-embedding-based triage methods for the bug triage problem. Additionally, the proposed method performs the best for adding new developers to an existing bug triage system without requiring retraining using a whole dataset.

show abstract

Section: Conventional Machine Learning-based Bug Triagementioning

confidence: 99%

Toward an Effective Bug Triage System Using Transformers to Add New Developers

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…We found the work of Yao et al to be highly relevant to our research. Consequently, we proposed a heterogeneous graphbased bug triage method that used GCN for learning a graph to predict the allocation of appropriate developers to bug reports [7]. A heterogeneous graph was built using the summaries and descriptions of the bug reports.…”

Section: Motivation and Previous Workmentioning

confidence: 99%

“…As mentioned in Section IV-B, different methods were used to weight the word-word edges: JS, Euclidean similarity, Pearson correlation, dice similarity, Hellinger similarity, and point-wise mutual information. The cosine similarity was used in previous work [7] for word-word edges weighting. The experimental results demonstrate the superiority of PMI compared to the other methods on all five datasets.…”

Section: Addressing the Research Questionsmentioning

confidence: 99%

See 1 more Smart Citation

A Graph Convolution Network-Based Bug Triage System to Learn Heterogeneous Graph Representation of Bug Reports

2022

Self Cite

View full text Add to dashboard Cite

Many bugs and defects occur during software testing and maintenance. These bugs should be resolved as soon as possible, to improve software quality. However, bug triage aims to solve these bugs by assigning the reported bugs to an appropriate developer or list of developers. It is an arduous task for a human triager to assign an appropriate developer to a bug report, when there are several developers with different skills, and several automated and semi-automated triage systems have been proposed in the last decade. Some recent techniques have suggested possibilities for the development of an effective triage system. However, these techniques require improvement. In previous work, we proposed a heterogeneous graph representation for bug triage, using word-word edges and word-bug document co-occurrences to build a heterogeneous graph of bug data. Cosine similarity is used to weight the word-word edges. Then, a graph convolution network is used to learn a heterogeneous graph representation. This paper extends our previous work by adopting different similarity metrics and correlation metrics for weighting word-word edges. The method was validated using different small and large datasets obtained from large-scale opensource projects. The top-k accuracy metric was used to evaluate the performance of the bug triage system. The experimental results showed that the point-wise mutual information of the proposed model was better than that of other word-word weighting methods, and our method had better accuracy for large datasets than other recent state-of-the-art methods.

show abstract

“…Zaidi and Lee (2021) developed a fixer recommendation approach that used a graph neural network (GNN) based on Yao, Mao and Luo (2019)'s work. Zaidi and Lee (2021) used a heterogeneous graph to represent the word-to-word relation and word-to-bug report relation. They evaluated their approach with Lee et al (2017)'s and Mani, Sankaran and Aralikatte (2019)'s methods.…”

Section: Fixer Recommendationmentioning

confidence: 99%

Heterogeneous information network to support the bug report resolution process

Barbosa¹

View full text Add to dashboard Cite

Contexto. Ao longo do ciclo de vida de um software, inúmeros documentos (por exemplo, relatórios de incidentes e código fonte) são produzidos por stakeholders. Os relatórios de incidentes (RI) são os principais documentos de insumo para apoiar as atividades (predição da severidade de relatórios de incidentes e recomendação de responsáveis pela correção do software) do processo de resolução de relatórios de incidentes (RRI). Já o código fonte combinado com os relatórios de incidentes são insumos para apoiar atividades de localização de defeitos. A Automação dessas atividades do processo RRI requer uma preocupação em como obter uma representação semanticamente representativa. Tradicionalmente utiliza-se Bag-of-Word (BoW) para representar os documentos de software para apoiar a execução automática dessas atividades por meio de algoritmos de aprendizado de máquina. Lacuna. No entanto, pouca atenção foi dada para representações baseadas em redes de informações heterogêneas (RIH), que permitem representar redes complexas respeitando os relacionamentos entre diferentes objetos. Contribuição. Esta tese de doutorado contribui para o avanço do estado da arte no que se refere aos modelos de representação de informações para apoiar a execução automática de atividades do processo RRI. Também avança na investigação de (i) algoritmos semissupervisionados que utilizam redes heterogêneas bipartidas para apoiar a predição de severidade de RI, (ii) um método que combina a representação BoW e redes de informações heterogêneas para apoiar a atividade de localização de defeitos, e (iii) uma abordagem holística que reutilizar uma rede de informações heterogêneas para apoiar atividades de RRI. Resultados. Os resultados demonstram que redes de informações heterogêneas podem ser uma alternativa promissora para apoiar a automação do processo RRI. Conclusões. Um processo RRI automático numa perspectica holística utilizando rede de informações heterogêneas apresentou resultados promissores ao serem comparados com representações do estado da arte.

show abstract

Learning Graph Representation of Bug Reports to Triage Bugs using Graph Convolution Network

Cited by 14 publications

References 16 publications

Toward an Effective Bug Triage System Using Transformers to Add New Developers

Toward an Effective Bug Triage System Using Transformers to Add New Developers

A Graph Convolution Network-Based Bug Triage System to Learn Heterogeneous Graph Representation of Bug Reports

Heterogeneous information network to support the bug report resolution process

Contact Info

Product

Resources

About