DeMuVGN: Effective Software Defect Prediction Model by Learning Multi-view Software Dependency via Graph Neural Networks

TL;DR

DeMuVGN is a novel graph neural network model that learns multi-view software dependencies, including code, call, and developer relations, to improve defect prediction accuracy across various software projects.

Contribution

It introduces a multi-view dependency graph and leverages GNNs combined with SMOTE to enhance defect prediction, addressing limitations of previous code-only dependency methods.

Findings

Multi-view graphs improve F1 scores by 11.1% to 12.1%.

DeMuVGN boosts F1 scores by 17.4% to 45.8% within projects.

Model performs well in both mature and new software versions.

Abstract

Software defect prediction (SDP) aims to identify high-risk defect modules in software development, optimizing resource allocation. While previous studies show that dependency network metrics improve defect prediction, most methods focus on code-based dependency graphs, overlooking developer factors. Current metrics, based on handcrafted features like ego and global network metrics, fail to fully capture defect-related information. To address this, we propose DeMuVGN, a defect prediction model that learns multi-view software dependency via graph neural networks. We introduce a Multi-view Software Dependency Graph (MSDG) that integrates data, call, and developer dependencies. DeMuVGN also leverages the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance and enhance defect module identification. In a case study of eight open-source projects across 20 versions, DeMuVGN demonstrates significant improvements: i) models based on multi-view graphs improve F1 scores by 11.1% to 12.1% over single-view models; ii) DeMuVGN improves F1 scores by 17.4% to 45.8% in within-project contexts and by 17.9% to 41.0% in cross-project contexts. Additionally, DeMuVGN excels in software evolution, showing more improvement in later-stage software versions. Its strong performance across different projects highlights its generalizability. We recommend future research focus on multi-view dependency graphs for defect prediction in both mature and newly developed projects.