Applying deep learning to science is a new trend in recent years which leads DL engineering to become an important problem. Although training data preparation, model architecture design, and model training are the normal processes to build DL models, all of them are complex and costly. Therefore, reusing the open-sourced pre-trained model is a practical way to bypass this hurdle for developers. Given a specific task, developers can collect massive pre-trained deep neural networks from public sources for re-using. However, testing the performance (e.g., accuracy and robustness) of multiple DNNs and recommending which model should be used is challenging regarding the scarcity of labeled data and the demand for domain expertise. In this paper, we propose a labeling-free (LaF) model selection approach to overcome the limitations of labeling efforts for automated model reusing. The main idea is to statistically learn a Bayesian model to infer the models' specialty only based on predicted labels. We evaluate LaF using 9 benchmark datasets including image, text, and source code, and 165 DNNs, considering both the accuracy and robustness of models. The experimental results demonstrate that LaF outperforms the baseline methods by up to 0.74 and 0.53 on Spearman's correlation and Kendall's $\tau$, respectively.
翻译:将深层次的学习应用到科学是近年来的新趋势,它导致DL工程成为一个重要的问题。尽管培训数据编制、模型架构设计和模型培训是建立DL模型的正常过程,但所有这些模型都是复杂和昂贵的。因此,重新使用开放源码的预科培训模型是绕过开发者这一障碍的实用方法。鉴于一项具体任务,开发者可以从公共来源收集大量预先培训的深层神经网络,以便重新使用。然而,测试多个DNNS的性能(例如准确性和稳健性)和建议应使用哪种模型对于标签数据稀缺和对域内专门知识的需求具有挑战性。在本文中,我们建议采用无标签(LAF)模型选择方法,以克服自动模型重新使用标签工作的局限性。主要想法是从统计学学学学一种贝伊斯模型,以便仅根据预测的标签来推断模型的专长。我们用9个基准数据集(包括图像、文本和源代码)和165 DNNWs来评估LAF的性能(例如图像、文本和源代码)和建议应该使用哪种模型的性,这是对标签数据缺乏的准确性和坚固度的挑战。在模型的精确性和坚固度方面都是挑战。我们建议了无标签模型中建议采用无标签的模型的模型的模型。我们建议了无标签模式中建议一种免模式的模型。我们建议了无标签式模型的模型选择的模型的模型的模型的模型选择的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型选择方法,我们。我们用。我们用。我们的实验结果,以显示的实验性能和比。我们用到0.基比。我们用到0.基比。我们的实验性,用到0.基比。实验性,通过SVER的基到0.和比。实验性,通过SVER的基法的基法。通过Sped的模型的模型的模型的比。实验性,用。