Just-In-Time Software Defect Prediction via Bi-modal Change Representation Learning

TL;DR

This paper introduces BiCC-BERT, a bi-modal change representation model pre-trained on code and commit messages, significantly improving just-in-time defect prediction accuracy by capturing deeper semantic information.

Contribution

The paper proposes a novel bi-modal pre-training model, BiCC-BERT, with a new RMI objective, and integrates it into JIT defect prediction, outperforming existing methods.

Findings

JIT-BiCC achieves 10.8% higher F1-score than baselines.

BiCC-BERT effectively captures semantic relations between code changes and messages.

The approach demonstrates the importance of natural language semantics in defect prediction.

Abstract

For predicting software defects at an early stage, researchers have proposed just-in-time defect prediction (JIT-DP) to identify potential defects in code commits. The prevailing approaches train models to represent code changes in history commits and utilize the learned representations to predict the presence of defects in the latest commit. However, existing models merely learn editions in source code, without considering the natural language intentions behind the changes. This limitation hinders their ability to capture deeper semantics. To address this, we introduce a novel bi-modal change pre-training model called BiCC-BERT. BiCC-BERT is pre-trained on a code change corpus to learn bi-modal semantic representations. To incorporate commit messages from the corpus, we design a novel pre-training objective called Replaced Message Identification (RMI), which learns the semantic association between commit messages and code changes. Subsequently, we integrate BiCC-BERT into JIT-DP and propose a new defect prediction approach -- JIT-BiCC. By leveraging the bi-modal representations from BiCC-BERT, JIT-BiCC captures more profound change semantics. We train JIT-BiCC using 27,391 code changes and compare its performance with 8 state-of-the-art JIT-DP approaches. The results demonstrate that JIT-BiCC outperforms all baselines, achieving a 10.8% improvement in F1-score. This highlights its effectiveness in learning the bi-modal semantics for JIT-DP.