基于多头自注意力机制的深度缺陷分派模型

计算机与现代化 ›› 2021, Vol. 0 ›› Issue (11): 39-43.

基于多头自注意力机制的深度缺陷分派模型

(1.青岛科技大学信息科学技术学院,山东青岛266061；2.山东信息职业技术学院,山东潍坊261061)

出版日期:2021-12-13 发布日期:2021-12-13
作者简介:万发洋(1996—),男，山东临沂人，硕士研究生，研究方向：推荐系统，数据挖掘，E-mail： wfyqdust@163.com；于旭(1982—),男，山东青岛人，副教授，博士，研究方向：推荐系统，数据挖掘，E-mail： yuxu0532@qust.edu.cn；徐其江(1981—),男，山东潍坊人，副教授，硕士，研究方向：推荐系统，数据挖掘，E-mail： xqj_1452@163.com。
基金资助:
国家自然科学基金资助项目（61402246, 61273180, 61375067， 61773384）；山东省自然科学基金资助项目（ZR2019MF014）；山东省重点研发计划项目(2018GGX101052)

Deep Bug Triage Model Based on Multi-head Self-attention Mechanism

(1. College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China;
2. Shandong Vocational College of Information Technology, Weifang 261061, China)

Online:2021-12-13 Published:2021-12-13

摘要/Abstract

摘要： 当前，缺陷跟踪系统通过缺陷报告实现缺陷与修复者的匹配。然而，以往的缺陷分派模型过于依赖缺陷报告的文本质量，引入自然语言中大量的冗余信息，并忽略了缺陷报告的元字段作为标签属性时存在于修复者之间的社区关系，使得模型结果表现较差。针对以上问题，本文提出一种基于多头自注意力机制的深度缺陷分派模型MSDBT(Multi-head Self-attention Deep Bug Triage)。对缺陷报告的文本内容以及根据元字段生成的修复者序列进行向量化；通过多头自注意力机制在内部的输入元素之间进行并行注意力计算。在4个开源软件项目上的实验结果表明，MSDBT在召回率指标上较之前模型具有明显的优势。

关键词: 缺陷跟踪系统, 缺陷分派, 深度学习, 修复者社区, 多头自注意力机制

Abstract: At present, bug tracking system realizes the matching of bug and fixer through bug report. However, the previous bug triage model relies too much on the text quality of the bug report, introduces a lot of redundant information in natural language, and ignores the community relationship between the fixers when the meta field of the bug report is used as the label attribute, which makes the model performance worse. Aiming at the above problems, this paper proposes a multi-head self-attention deep bug triage (MSDBT). The text description of the bug report and the fixer sequence generated from meta field are vectorized; the multi-head self-attention mechanism is used to perform parallel attention calculation among the internal input elements. The results of experiments on four open source software projects show that MSDBT has obvious advantages over the previous model in terms of recall index.

Key words: bug tracking system, bug triage, deep learning, fixer community, multi-head self-attention mechanism

万发洋, 于旭, 徐其江. 基于多头自注意力机制的深度缺陷分派模型[J]. 计算机与现代化, 2021, 0(11): 39-43.

WAN Fa-yang, YU Xu, XU Qi-jiang. Deep Bug Triage Model Based on Multi-head Self-attention Mechanism[J]. Computer and Modernization, 2021, 0(11): 39-43.

参考文献［23］

［1］	CUBRANIC D, MURPHY G C. Automatic bug triage using text categorization［C］// Proceedings of the 16th International Conference on Software Engineering & Knowledge Engineering. 2004:92-97.
［2］	TAMRAWI A, NGUYEN T T, AL-KOFAHI J M, et al. Fuzzy set and cache-based approach for bug triaging［C］// Proceedings of the 19th ACM SIGSOFT Symposium and the 13th European Conference on Foundations of Software Engineering. 2011:365-375.
［3］	XUAN J F, JIANG H, REN Z L, et al. Developer prioritization in bug repositories［C］// Proceedings of the 34th International Conference on Software Engineering. 2012:25-35.
［4］	ANVIK J, HIEW L, MURPHY G C. Who should fix this bug?［C］// Proceedings of the 28th International Conference on Software Engineering. 2006:361-370.
［5］	TIAN Y, WIJEDASA D, LO D, et al. Learning to rank for bug report assignee recommendation［C］// Proceedings of the 24th IEEE International Conference on Program Comprehension. 2016. DOI: 10.1109/ICPC.2016.7503715.
［6］	GAY G, HAIDUC S, MARCUS A, et al. On the use of relevance feedback in IR-based concept location［C］// Proceedings of the 25th IEEE International Conference on Software Maintenance. 2009:351-360.
［7］	YE X, BUNESCU R， LIU C. Learning to rank relevant files for bug reports using domain knowledge［C］// Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering. 2014:689-699.
［8］	XIA X, LO D, DING Y, et al. Improving automated bug triaging with specialized topic model［J］. IEEE Transactions on Software Engineering, 2017,43(3):272-297.
［9］	YANG G, ZHANG T, LEE B. Towards semi-automatic bug triage and severity prediction based on topic model and multi-feature of bug reports［C］// Proceedings of the IEEE 38th Annual Computer Software and Applications Conference. 2014:97-106.〖HJ1.42mm〗
［10］	XIE X H, ZHANG W, YANG Y, et al. DRETOM: Developer recommendation based on topic models for bug resolution［C］// Proceedings of the 8th International Conference on Predictive Models in Software Engineering. 2012:19-28.
［11］	XIA X, LO D, WANG X Y, et al. Dual analysis for recommending developers to resolve bugs［J］. Journal of Software:Evolution and Process, 2015,27(3):195-220.
［12］	LEE S R, HEO M J, LEE C G, et al. Applying deep learning based automatic bug triager to industrial projects［C］// Proceedings of the 11th Joint Meeting on Foundations of Software Engineering. 2017:926-931.
［13］	MANI S, SANKARAN A, ARALIKATTE R. DeepTriage: Exploring the effectiveness of deep learning for bug triaging［C］// Proceedings of the 2019 ACM India Joint International Conference on Data Science and Management of Data. 2019:171-179.
［14］	席圣渠，姚远，徐锋，等. 基于循环神经网络的缺陷报告分派方法［J］. 软件学报, 2018,29（8）:2322-2335.
［15］	刘烨,黄金筱,马于涛. 基于混合神经网络和注意力机制的软件缺陷自动分派方法［J］. 计算机研究与发展, 2020,57(3):459-473.
［16］	宋化志,马于涛. DeepTriage:一种基于深度学习的软件缺陷自动分配方法［J］. 小型微型计算机系统, 2019,40(1):126-132.
［17］	李元香,董夏磊,项正龙，等. 基于图卷积神经网络的软件缺陷分派方法［J］. 武汉大学学报（理学版）, 2020,66(3):244-252.
［18］	WU W J, ZHANG W, YANG Y, et al. DREX: Developer recommendation with k-nearest-neighbor search and expertise ranking［C］// Proceedings of the 18th Asia-Pacific Software Engineering Conference. 2011:389-396.
［19］	JEONG G, KIM S, ZIMMERMANN T. Improving bug triage with bug tossing graphs［C］// Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering. 2009:111-120.
［20］	BHATTACHARYA P, NEAMTIU I. Fine-grained incremental learning and multi-feature tossing graphs to improve bug triaging［C］// Proceedings of the 2010 IEEE International Conference on Software Maintenance. 2010. DOI: 10.1109/ICSM.2010.5609736.
［21］	ZHANG W, WANG S, WANG Q. KSAP: An approach to bug report assignment using KNN search and heterogeneous proximity［J］. Information and Software Technology, 2016,70:68-84.
［22］	NAGUIB H, NARAYAN N, BRUGGE B, et al. Bug report assignee recommendation using activity profiles［C］// Proceedings of the 10th Working Conference on Mining Software Repositories. 2013:22-30.
［23］	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017:6000-6010.

[1]	胡崇佳, 刘金洲, 方立. 基于无监督域适应的室外点云语义分割[J]. 计算机与现代化, 2024, 0(01): 74-79.
[2]	林威. 基于自监督学习和数据回放的新闻推荐模型增量学习方法[J]. 计算机与现代化, 2023, 0(12): 1-6.
[3]	梁天恺, 黄康华, 刘凯航, 兰岚, 曾碧. 基于双向同态加密的深度联邦图片分类方法[J]. 计算机与现代化, 2023, 0(12): 36-40.
[4]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[5]	张伯泉, 麦海鹏, 陈嘉敏, 逄锦聚. 基于高灰度值注意力机制的脑白质高信号分割[J]. 计算机与现代化, 2023, 0(12): 67-75.
[6]	马泽宇, 叶宁, 徐康, 王甦, 王汝传, . 基于FMCW雷达和ResNeSt-GRU的行为识别方法[J]. 计算机与现代化, 2023, 0(11): 101-107.
[7]	李延满, 王必恒, 赵羚焱. 基于轻量化YOLOv5的安全帽检测[J]. 计算机与现代化, 2023, 0(10): 59-64.
[8]	黎世达, 项剑文. 一种提高图像识别模型鲁棒性的弱化强化方法[J]. 计算机与现代化, 2023, 0(10): 70-76.
[9]	沈加炜, 陆一鸣, 陈晓艺, 钱美玲, 陆卫忠, . 基于深度学习的人体行为检测方法研究综述[J]. 计算机与现代化, 2023, 0(09): 1-9.
[10]	刘禅奕, 黄丹, 薛林雁, 王涛, 朱桃, . 改进EfficientNet网络的COVID-19 X光分类[J]. 计算机与现代化, 2023, 0(09): 94-99.
[11]	马国祥, 杨凌菲, 严传波, 张志豪, 孙彬, 王晓荣. 基于深度DenseNet网络的肝包虫病超声影像诊断方法[J]. 计算机与现代化, 2023, 0(09): 100-104.
[12]	农皓程, 任德均, 任秋霖, 刘澎笠, 黄德成. 基于改进ConvNeXt的软塑包装表面异常检测算法[J]. 计算机与现代化, 2023, 0(08): 12-17.
[13]	欧阳飞, 吴旭, 向东升. 基于改进YOLOX的垃圾分类检测方法[J]. 计算机与现代化, 2023, 0(08): 68-73.
[14]	胡睿杰, 车逗. 红外小目标检测方法综述[J]. 计算机与现代化, 2023, 0(08): 79-86.
[15]	江蕾, 唐建, 杨超越, 吕婷婷. 基于CWGAN-GP与CNN的轴承故障诊断方法[J]. 计算机与现代化, 2023, 0(07): 1-6.