paperbot · PL 论文追踪

全部论文 待读 收藏

P2 A universal data augmentation approach for fault localization

一种面向故障定位的通用数据增强方法
ICSE Proceedings of the 44th International Conference on Software Engineering2022匹配度 2/10 · 该论文属于软件测试与故障定位中的机器学习数据增强,与用户核心关注的静态分析、LLM/Agent 与程序分析交叉、浮点程序分析及贝叶斯程序分析均无直接关系。其问题设定和贡献也不涉及形式化或工业级静态分析工具落地。引用 61 inbox
Huan Xie, Yan Lei, Meng Yan, Yue Yu, Xin Xia, Xiaoguang Mao
crossref: 2026-09-12dblp: 2026-09-12

AI 速览

一句话:提出一种通用数据增强方法,缓解故障定位中输入数据高维且极不平衡的问题,以提升定位技术有效性。

故障定位(FL)技术通常以代码覆盖矩阵和失败向量作为输入,期望从程序实体与失败的关联中定位缺陷。然而真实程序规模大,且失败测试用例远少于通过用例,导致输入数据具有高维和极度不平衡的特点,严重影响定位技术的有效性。本文提出一种通用的数据增强方法,针对故障定位任务缓解上述数据高维与类别不平衡问题,以提升现有 FL 技术的有效性。摘要未给出具体实验设置与结果。

问题
故障定位技术依赖代码覆盖矩阵与失败向量,但真实程序导致输入数据高维,且失败用例远少于通过用例,数据极度不平衡,损害 FL 有效性。
方法
提出一种通用的数据增强方法,面向故障定位任务,旨在缓解输入数据的高维与类别不平衡问题,以提升现有 FL 技术的有效性。
评估
摘要未报告具体的评估方法、数据集与实验结果。
原文摘要(Abstract)

Data is the fuel to models, and it is still applicable in fault localization (FL). Many existing elaborate FL techniques take the code coverage matrix and failure vector as inputs, expecting the techniques could find the correlation between program entities and failures. However, the input data is high-dimensional and extremely unbalanced since the real-world programs are large in size and the number of failing test cases is much less than that of passing test cases, which are posing severe threats to the effectiveness of FL techniques.

链接与引用

DOI 原文 · DBLP

BibTeX
@inproceedings{XieLY00M22,
  title = {A universal data augmentation approach for fault localization},
  author = {Huan Xie and Yan Lei and Meng Yan and Yue Yu and Xin Xia and Xiaoguang Mao},
  booktitle = {ICSE},
  year = {2022},
  doi = {10.1145/3510003.3510136}
}