Enhancing Code Representation for Improved Graph Neural Network-Based Fault Localization
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it