Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yuze Jiang, Beijun Shen, Xiaodong Gu

TL;DR

A novel bi-modal change pre-training model called BiCC-BERT is introduced and integrated into JIT-DP and it is demonstrated that JIT-BiCC outperforms all baselines, achieving a 10.8% improvement in F1-score.

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.

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

TL;DR

A novel bi-modal change pre-training model called BiCC-BERT is introduced and integrated into JIT-DP and it is demonstrated that JIT-BiCC outperforms all baselines, achieving a 10.8% improvement in F1-score.

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.

Paper Structure

This paper contains 29 sections, 5 equations, 6 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Background and Motivation
  3. Just-In-Time Defect Prediction
  4. Code Change Representations
  5. Approach
  6. Learning Code Change Representations
  7. Model Architecture
  8. Masked Language Modeling (MLM)
  9. Replaced Message Identification (RMI)
  10. Just-In-Time Defect Prediction
  11. Feature Extraction and Fusion
  12. Defect Prediction
  13. Experimental Setup
  14. Research Questions
  15. Dataset
  16. ...and 14 more sections

Figures (6)

  • Figure 1: An illustration of a defect-inducing code change
  • Figure 2: Fixing patch to the defective code change in Figure 1
  • Figure 3: An illustration of the importance of commit messages
  • Figure 4: The architecture of BiCC-BERT
  • Figure 5: Illustration of the pre-training objectives
  • ...and 1 more figures