D&C: A Divide-and-Conquer Approach to IR-based Bug Localization

TL;DR

This paper introduces D&C, a divide-and-conquer machine learning approach that improves IR-based bug localization accuracy by training multiple classifiers on specific bug report sets, outperforming existing tools.

Contribution

The paper presents a novel learning-based method that assigns optimal weights to similarity measures, significantly enhancing bug localization performance over state-of-the-art tools.

Findings

D&C achieves higher MAP and MRR scores than existing tools.

D&C locates around 50% of bugs at Top1, 77% at Top5, and 85% at Top10.

The approach demonstrates stable and substantial improvements in bug localization accuracy.

Abstract

Many automated tasks in software maintenance rely on information retrieval techniques to identify specific information within unstructured data. Bug localization is such a typical task, where text in a bug report is analyzed to identify file locations in the source code that can be associated to the reported bug. Despite the promising results, the performance offered by IR-based bug localization tools is still not significant for large adoption. We argue that one reason could be the attempt to build a one-size-fits-all approach. In this paper, we extensively study the performance of state-of-the-art bug localization tools, focusing on query formulation and its importance with respect to the localization performance. Building on insights from this study, we propose a new learning approach where multiple classifier models are trained on clear-cut sets of bug-location pairs. Concretely, we apply a gradient boosting supervised learning approach to various sets of bug reports whose localizations appear to be successful with specific types of features. The training scenario builds on our findings that the various state-of-the-art localization tools can be highly performant for specific sets of bug reports. We implement D&C, which computes appropriate weights that should be assigned to the similarity measurements between pairs of information token types. Experimental results on large and up-to-date datasets reveal that D&C outperforms state-of-the-art tools. On average, the experiments yield an MAP score of 0.52, and an MRR score of 0.63 with a curated dataset, which provides a substantial performance improvement over all tools: MAP is improved by between 4 and up to 10 percentage points, while MRR is improved by between 1 and up to 12. Finally, we note that D&C is stable in its localization performance: around 50% of bugs can be located at Top1, 77% at Top5 and 85% at Top10.