Enhancing Code Representation for Improved Graph Neural Network-Based Fault Localization

Abstract

Software fault localization in complex systems poses significant challenges. Traditional spectrum-based methods (SBFL) and newer learning-based approaches often fail to fully grasp the software’s complexity. Graph Neural Network (GNN) techniques, which model code as graphs, show promise but frequently overlook method in- teractions and code evolution. This paper introduces DepGraph, utilizing Gated Graph Neural Networks (GGNN) to incorporate interprocedural method calls and historical code changes, aiming for a more comprehensive fault localization. DepGraph’s graph rep- resentation merges code structure, method calls, and test coverage to enhance fault detection. Tested against the Defects4j bench- mark, DepGraph surpasses existing methods, notably improving fault detection by 13% at Top-1 and significantly improving Mean First Rank (MFR) and Mean Average Rank (MAR) by over 50%. It effectively utilizes historical code changes, boosting fault identi- fication by 20% at Top-1. Additionally, DepGraph’s optimization techniques reduce graph size by 70% and lower GPU memory use by 44%, indicating efficiency gains for GNN-based fault localization. In cross-project scenarios, DepGraph shows exceptional adaptability and performance, with a 42% increase in Top-1 accuracy and sub- stantial improvements in MFR and MAR, highlighting its robustness and versatility in various software environments.