Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

5-2019

Abstract

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the hierarchical and sequential structure of a code change, differentiating it from the existing deep learning models on source code. PatchNet provides several options allowing users to select parameters for the training process. The tool has been validated in the context of automatic identification of stable-relevant patches in the Linux kernel and is potentially applicable to automate other software engineering tasks that can be formulated as patch classification problems. Our video demonstrating PatchNet and PatchNet implementation are publicly available at https://goo.gl/CZjG6X and https://github.com/hvdthong/PatchNetTool respectively.

Keywords

Deep learning, Patch classification, Stable patch identification

Discipline

Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

41st IEEE/ACM International Conference on Software Engineering: ICSE-Companion 2019: Montreal, 25-31 May: Proceedings

First Page

83

Last Page

86

ISBN

9781728117645

Identifier

10.1109/ICSE-Companion.2019.00044

Publisher

IEEE

City or Country

Piscataway, NJ

Embargo Period

12-18-2019

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/ICSE-Companion.2019.00044

Download

Share

COinS