Exploring the efficacy of transfer learning in mining image-based software artifacts
Exploring the efficacy of transfer learning in mining image-based software artifacts
复制标题
DOI：
10.1186/s40537-020-00335-4
复制
发表时间：
2020-12-08
影响因子：
8.1
通讯作者：
Linstead, Erik J.
中科院分区：
文献类型：
--
作者：
Best, Natalie;Ott, Jordan;Linstead, Erik J.
迁移学习允许我们通过利用先前为另一项任务训练的现有模型来训练需要大量学习参数的深度架构，即使可用数据量有限。在之前尝试在缺乏大数据的情况下对基于图像的软件工件进行分类时，注意到标准现成的深度架构（如VGG）由于其较大的参数空间而无法使用，因此必须由具有较少层的定制架构取代。这被证明是具有挑战性的经验软件工程师谁愿意利用现有的架构，而不需要customization.FindingsHere的，我们探讨了迁移学习的适用性，利用模型预训练的非软件工程数据应用到分类软件统一建模语言（UML）图的问题。我们的实验结果表明，训练对迁移学习的反应与样本大小有关，即使预先训练的模型没有暴露于软件领域的训练实例。我们将转移网络与其他网络进行对比，以显示其在不同大小的训练集上的优势，这表明当大量训练数据不可用时，转移学习在分类准确性方面对自定义深度架构同样有效。结论我们的研究结果表明，即使基于不包含软件工程工件的模型，可以为使用现成的深度架构而无需定制提供途径。这为那些希望将深度学习应用于基于图像的分类但没有专业知识或舒适度来定义自己的网络架构的从业者提供了一种替代方案。
BackgroundTransfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. In previous attempts to classify image-based software artifacts in the absence of big data, it was noted that standard off-the-shelf deep architectures such as VGG could not be utilized due to their large parameter space and therefore had to be replaced by customized architectures with fewer layers. This proves to be challenging to empirical software engineers who would like to make use of existing architectures without the need for customization.FindingsHere we explore the applicability of transfer learning utilizing models pre-trained on non-software engineering data applied to the problem of classifying software unified modeling language (UML) diagrams. Our experimental results show training reacts positively to transfer learning as related to sample size, even though the pre-trained model was not exposed to training instances from the software domain. We contrast the transferred network with other networks to show its advantage on different sized training sets, which indicates that transfer learning is equally effective to custom deep architectures in respect to classification accuracy when large amounts of training data is not available.ConclusionOur findings suggest that transfer learning, even when based on models that do not contain software engineering artifacts, can provide a pathway for using off-the-shelf deep architectures without customization. This provides an alternative to practitioners who want to apply deep learning to image-based classification but do not have the expertise or comfort to define their own network architectures.