arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.03395cs.SEcs.LG
收藏

Manas：挖掘软件仓库以帮助AutoML

Manas: Mining Software Repositories to Assist AutoML

Iowa State University（爱荷华州立大学）

Giang Nguyen, Md Johir Islam, Rangeet Pan, Hridesh Rajan

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

如今，深度学习被广泛用于构建软件。深度学习的一个软件工程问题是，为任务找到合适的卷积神经网络（CNN）模型对开发人员来说可能是一个挑战。最近关于AutoML的工作，更准确地说是神经架构搜索（NAS），通过Auto-Keras等工具实现，旨在解决这个问题，基本上将其视为一个搜索问题，其中起点是默认的CNN模型，并且该CNN模型的突变允许探索CNN模型的空间，以找到最适合该问题的CNN模型。这些工作在产生高精度CNN模型方面取得了重大成功。然而，有两个问题。首先，NAS可能非常昂贵，通常需要几个小时才能完成。其次，NAS生成的CNN模型可能非常复杂，这使得理解它们变得更加困难，并且训练它们的成本也更高。我们提出了一种新的NAS方法，其中不是从默认的CNN模型开始，而是从GitHub提取的模型库中选择初始模型。直觉是，与默认模型相比，解决类似问题的开发人员可能已经开发了一个更好的起点。我们还分析了野外CNN模型的常见层模式，以了解开发人员为改进模型而做出的更改。我们的方法使用通常发生的变化作为NAS中的变异算子。我们扩展了Auto-Keras来实现我们的方法。我们使用Kaggle的8个投票最高的问题进行评估，包括图像分类和图像回归，结果显示，在相同的搜索时间下，在不损失准确性的情况下，Manas生成的模型比Auto-Keras的模型少42.9%到99.6%的参数。以GPU为基准，Manas的模型训练速度比Auto-Keras的模型快30.3%至641.6%。

英文摘要：

Today deep learning is widely used for building software. A software engineering problem with deep learning is that finding an appropriate convolutional neural network (CNN) model for the task can be a challenge for developers. Recent work on AutoML, more precisely neural architecture search (NAS), embodied by tools like Auto-Keras aims to solve this problem by essentially viewing it as a search problem where the starting point is a default CNN model, and mutation of this CNN model allows exploration of the space of CNN models to find a CNN model that will work best for the problem. These works have had significant success in producing high-accuracy CNN models. There are two problems, however. First, NAS can be very costly, often taking several hours to complete. Second, CNN models produced by NAS can be very complex that makes it harder to understand them and costlier to train them. We propose a novel approach for NAS, where instead of starting from a default CNN model, the initial model is selected from a repository of models extracted from GitHub. The intuition being that developers solving a similar problem may have developed a better starting point compared to the default model. We also analyze common layer patterns of CNN models in the wild to understand changes that the developers make to improve their models. Our approach uses commonly occurring changes as mutation operators in NAS. We have extended Auto-Keras to implement our approach. Our evaluation using 8 top voted problems from Kaggle for tasks including image classification and image regression shows that given the same search time, without loss of accuracy, Manas produces models with 42.9% to 99.6% fewer number of parameters than Auto-Keras' models. Benchmarked on GPU, Manas' models train 30.3% to 641.6% faster than Auto-Keras' models.

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。

↑