arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.05515cs.SEcs.LG
收藏

机器/深度学习与软件工程之间的协同:我们离成功还有多远?

Synergy between Machine/Deep Learning and Software Engineering: How Far Are We?

Southern Methodist University(南卫理公会大学);Nanjing University(南京大学);University of Texas at Dallas(德克萨斯大学达拉斯分校)

Simin Wang, Liguo Huang, Jidong Ge, Tengfei Zhang, Haitao Feng, Ming Li, He Zhang, Vincent Ng

摘要:

自2009年以来,由ImageNet引入引发的深度学习革命激发了机器学习(ML)/深度学习(DL)和软件工程(SE)之间的协同作用。与此同时,出现了一些批评性的评论,建议ML/DL应该谨慎使用。为了提高ML/DL相关SE研究的质量(特别是适用性和普遍性),并刺激和加强SE/AI研究人员与行业从业者之间的未来合作,我们对2009年至2018年期间发表的906篇ML/DL相关SE论文进行了为期10年的系统文献综述(SLR)。我们的趋势分析表明,ML/DL和SE相互影响。然而,与此同时,我们也观察到缺乏可复制和可重复的ML/DL相关SE研究,并确定了影响其可复制性和可重复性的五个因素。为了提高研究结果的适用性和普遍性,我们分析了研究中的哪些成分有助于理解为什么选择ML/DL技术来解决特定的SE问题。此外,我们确定了DL模型对SE任务影响的独特趋势,以及为了更好地利用DL来提高SE任务的生产力而需要满足的五个独特挑战。最后,我们概述了一个路线图,我们相信它可以促进基于ML/DL的SE研究成果转化为现实世界的行业实践。

英文摘要:

Since 2009, the deep learning revolution, which was triggered by the introduction of ImageNet, has stimulated the synergy between Machine Learning (ML)/Deep Learning (DL) and Software Engineering (SE). Meanwhile, critical reviews have emerged that suggest that ML/DL should be used cautiously. To improve the quality (especially the applicability and generalizability) of ML/DL-related SE studies, and to stimulate and enhance future collaborations between SE/AI researchers and industry practitioners, we conducted a 10-year Systematic Literature Review (SLR) on 906 ML/DL-related SE papers published between 2009 and 2018. Our trend analysis demonstrated the mutual impacts that ML/DL and SE have had on each other. At the same time, however, we also observed a paucity of replicable and reproducible ML/DL-related SE studies and identified five factors that influence their replicability and reproducibility. To improve the applicability and generalizability of research results, we analyzed what ingredients in a study would facilitate an understanding of why a ML/DL technique was selected for a specific SE problem. In addition, we identified the unique trends of impacts of DL models on SE tasks, as well as five unique challenges that needed to be met in order to better leverage DL to improve the productivity of SE tasks. Finally, we outlined a road-map that we believe can facilitate the transfer of ML/DL-based SE research results into real-world industry practices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑