DeepReview: Automatic Code Review Using Deep Multi-instance Learning

Li, Heng-Yi; Shi, Shuting; Thung, Ferdian; Huo, Xuan; Xu, Bowen; Li, Ming; Lo, David

doi:10.1007/978-3-030-16145-3_25

Cited by 13 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, they also attempt to capture the relation of different hunks in a pull request by encoding each hunk and computing attention scores across diff hunks to fuse the information. Li et al [24] formalize automatic code review as a multi-instance learning task, in which each hunk is an instance and the target is to predict whether a pull request will be accepted.…”

Section: Automating Code Review Activitiesmentioning

confidence: 99%

CodeReviewer: Pre-Training for Automating Code Review Activities

Li¹,

Lü²,

Guo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Code review is an essential part to software development lifecycle since it aims at guaranteeing the quality of codes. Modern code review activities necessitate developers viewing, understanding and even running the programs to assess logic, functionality, latency, style and other factors. It turns out that developers have to spend far too much time reviewing the code of their peers. Accordingly, it is in significant demand to automate the code review process. In this research, we focus on utilizing pre-training techniques for the tasks in the code review scenario. We collect a large-scale dataset of real world code changes and code reviews from open-source projects in nine of the most popular programming languages. To better understand code diffs and reviews, we propose CodeReviewer, a pre-trained model that utilizes four pre-training tasks tailored specifically for the code review senario. To evaluate our model, we focus on three key tasks related to code review activities, including code change quality estimation, review comment generation and code refinement. Furthermore, we establish a high-quality benchmark dataset based on our collected data for these three tasks and conduct comprehensive experiments on it. The experimental results demonstrate that our model outperforms the previous state-of-theart pre-training approaches in all tasks. Further analysis show that our proposed pre-training tasks and the multilingual pre-training dataset benefit the model on the understanding of code changes and reviews.

show abstract

Section: Automating Code Review Activitiesmentioning

confidence: 99%

CodeReviewer: Pre-Training for Automating Code Review Activities

Li¹,

Lü²,

Guo³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They found that the change requests by inexperienced developers that involve many reviewers are the most likely to be rejected. In the same line of research, Li et al [162] used Deep Learning to predict a change's acceptance probability. Their approach, called DeepReview, outperformed traditional single-instance approaches.…”

Section: Support Systems For Codementioning

confidence: 99%

“…Recently, researchers have invested in using Deep Learning to aiming at code review automation [52,162,218]. Some studies have focused on identifying the difference between different code revisions [52,218], while Tufano et al [244] focused on providing an end-to-end solution, from identifying code changes to providing review comments.…”

Section: Support Systems For Codementioning

confidence: 99%

Modern Code Reviews—Survey of Literature and Practice

Badampudi

Unterkalmsteiner

Britto

2023

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

Background: Modern Code Review (MCR) is a lightweight alternative to traditional code inspections. While secondary studies on MCR exist; it is unknown whether the research community has targeted themes that practitioners consider important. Objectives: The objectives are to provide an overview of MCR research, analyze the practitioners’ opinions on the importance of MCR research, investigate the alignment between research and practice, and propose future MCR research avenues. Method: We conducted a systematic mapping study to survey state-of-the-art until and including 2021, employed the Q-Methodology to analyze the practitioners’ perception of the relevance of MCR research, and analyzed the primary studies’ research impact. Results: We analyzed 244 primary studies, resulting in five themes. As a result of the 1300 survey data points, we found that the respondents are positive about research investigating the impact of MCR on product quality and MCR process properties. In contrast, they are negative about human factor- and support systems-related research. Conclusion: These results indicate a misalignment between the state-of-the-art and the themes deemed important by most survey respondents. Researchers should focus on solutions that can improve the state of MCR practice. We provide an MCR research agenda, which can potentially increase the impact of MCR research.

show abstract

“…In this work, the code changes are regarded as a binary classification task, and the features of code are extracted by using a convolutional neural network and LSTM network, and the differential features of code changes are extracted by using the paired autoencoder model. Heng-Yi Li et al proposed a multi-instance-based automatic code review framework [20]. In this work, each code review is regarded as a multi-instance package containing multiple code change blocks, and an end-to-end model is proposed to extract the different features between the original code package and modified code package to predict whether the code review is passed.…”

Section: Code Reviewmentioning

confidence: 99%

Automatic Code Review by Learning the Structure Information of Code Graph

Yin

Zhao

Sun

et al. 2023

Sensors

View full text Add to dashboard Cite

At present, the explosive growth of software code volume and quantity makes the code review process very labor-intensive and time-consuming. An automated code review model can assist in improving the efficiency of the process. Tufano et al., designed two automated tasks to help improve the efficiency of code review based on the deep learning approach, from two different perspectives, namely, the developer submitting the code and the code reviewer. However, they only used code sequence information and did not explore the logical structure information with a richer meaning of the code. To improve the learning of code structure information, a program dependency graph serialization algorithm PDG2Seq algorithm is proposed, which converts the program dependency graph into a unique graph code sequence in a lossless manner, while retaining the program structure information and semantic information. We then designed an automated code review model based on the pre-trained model CodeBERT architecture, which strengthens the learning of code information by fusing program structure information and code sequence information, and then fine-tuned the model according to the code review activity scene to complete the automatic modification of the code. To verify the efficiency of the algorithm, the two tasks in the experiment were compared with the best Algorithm 1-encoder/2-encoder. The experimental results show that the model we proposed has a significant improvement under the BLEU, Lewinshtein distance and ROUGE-L metrics.

show abstract

DeepReview: Automatic Code Review Using Deep Multi-instance Learning

Cited by 13 publications

References 17 publications

CodeReviewer: Pre-Training for Automating Code Review Activities

CodeReviewer: Pre-Training for Automating Code Review Activities

Modern Code Reviews—Survey of Literature and Practice

Automatic Code Review by Learning the Structure Information of Code Graph

Contact Info

Product

Resources

About