CodeSage-GNN: Cross-Modal Graph Neural Network for Intelligent Software Defect Prediction
Journal of Computational Informatics & Business · 2025
DOI: 10.65606/32/2025/55 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational Informatics & Business, 2025. Verfasst von Armaghan Mubeen Butt und 2 weiteren Autor:innen.
Abstract (Originalsprache)
This study proposes CodeSage-GNN, a cross-modal graph neural framework for predicting defect-prone software modules. CodeSage-GNN represents each file or class as a heterogeneous graph combining structural metrics, dependency relations, and semantic embeddings of source code tokens. A dual-channel message-passing network jointly learns from structural graphs and textual semantics, while an attention-based fusion layer highlights the most influential features contributing to defects. The model is evaluated on multiple open software defect benchmarks to measure F1-score, MCC, AUC, and cross-project generalization. By integrating graph representation learning with interpretable attentions, CodeSage-GNN aims to support early fault localization and quality assurance in large-scale software systems.
Zitieren
APA
Butt, A. M., Waqar, M. Z., & MUHAMMAD-HASEEB-ZIA (2025). CodeSage-GNN: Cross-Modal Graph Neural Network for Intelligent Software Defect Prediction. Journal of Computational Informatics & Business. https://doi.org/10.65606/32/2025/55
Vancouver
Butt AM, Waqar MZ, MUHAMMAD-HASEEB-ZIA. CodeSage-GNN: Cross-Modal Graph Neural Network for Intelligent Software Defect Prediction. Journal of Computational Informatics & Business. 2025. doi:10.65606/32/2025/55
BibTeX
@article{Butt2025,
author = {Butt, Armaghan Mubeen and Waqar, Muhammad Zayaan and MUHAMMAD-HASEEB-ZIA},
title = {CodeSage-GNN: Cross-Modal Graph Neural Network for Intelligent Software Defect Prediction},
journal = {Journal of Computational Informatics & Business},
year = {2025},
doi = {10.65606/32/2025/55}
}
EUVIMED