Towards Better Graph Neural Network-Based Fault Localization through Enhanced Code Representation
Open Access
- 12 July 2024
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 1 (FSE) , 1937-1959
Abstract
Automatic software fault localization plays an important role in software quality assurance by pinpointing faulty locations for easier debugging. Coverage-based fault localization is a commonly used technique, which applies statistics on coverage spectra to rank faulty code based on suspiciousness scores. However, statisticsbased approaches based on formulae are often rigid, which calls for learning-based techniques. Amongst all, Grace , a graph-neural network (GNN) based technique has achieved state-of-the-art due to its capacity to preserve coverage spectra, i.e., test-to-source coverage relationships, as precise abstract syntax-enhanced graph representation, mitigating the limitation of other learning-based technique which compresses the feature representation. However, such representation is not scalable due to the increasing complexity of software, correlating with increasing coverage spectra and AST graph, making it challenging to extend, let alone train the graph neural network in practice. In this work, we proposed a new graph representation, DepGraph , that reduces the complexity of the graph representation by 70 % in nodes and edges by integrating the interprocedural call graph in the graph representation of the code. Moreover, we integrate additional features—code change information—into the graph as attributes so the model can leverage rich historical project data. We evaluate DepGraph using Defects4j 2.0.0, and it outperforms Grace by locating 20 % more faults in Top-1 and improving the Mean First Rank (MFR) and the Mean Average Rank (MAR) by over 50 % while decreasing GPU memory usage by 44 % and training/inference time by 85 % . Additionally, in cross-project settings, DepGraph surpasses the state-of-the-art baseline with a 42 % higher Top-1 accuracy, and 68 % and 65 % improvement in MFR and MAR, respectively. Our study demonstrates DepGraph ’s robustness, achieving state-of-the-art accuracy and scalability for future extension and adoption.Keywords
All Related Versions
This publication has 55 references indexed in Scilit:
- GNet4FL: effective fault localization via graph convolutional neural networkAutomated Software Engineering, 2023
- Graph Neural Networks: Scalability2022
- Fault Localization with Code Coverage Representation Learning2021
- Improving Software Fault Localization by Combining Spectrum and MutationIEEE Access, 2020
- Understanding of a convolutional neural network2017
- Deep Residual Learning for Image Recognition2016
- Metallaxis‐FL: mutation‐based fault localizationSoftware Testing, Verification and Reliability, 2013
- Where should the bugs be fixed? More accurate information retrieval-based bug localization based on bug reports2012
- Long Short-Term Memory2012
- Spectrum-Based Multiple Fault Localization2009