This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from log 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 demonstration on the performance of PatchNet is publicly available at https://goo.gl/CZjG6X.
Fri 31 MayDisplayed time zone: Eastern Time (US & Canada) change
11:00 - 12:30
|The List is the Process: Reliable Pre-Integration Tracking of Commits on Mailing ListsTechnical Track|
|Graph-based Mining of In-the-Wild, Fine-grained, Semantic Code Change PatternsTechnical Track|
|Coming: a Tool for Mining Change Pattern Instances from Git CommitsDemos|
|PatchNet: A Tool for Deep Patch ClassificationDemos|