arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.05319cs.SEcs.LGstat.ML
收藏

比深度学习快500倍以上(探索更快方法进行StackOverflow文本挖掘的案例研究)

500+ Times Faster Than Deep Learning (A Case Study Exploring Faster Methods for Text Mining StackOverflow)

NC State(北卡罗来纳州立大学)

Suvodeep Majumder, Nikhila Balaji, Katie Brey, Wei Fu, Tim Menzies

AI总结:

本文针对StackOverflow文本挖掘,提出基于聚类和局部SVM调优的方法,比深度学习快500倍以上且F1分数仅低不到2%,建议研究者在发布复杂方法前先与简单替代方案进行对比。

摘要:

深度学习方法对高维数据很有用,在软件工程的许多领域正得到广泛应用。深度学习器利用大量计算能力且训练时间可能很长,这使得广泛验证、重复和改进其结果变得困难。此外,它们并非所有领域的最佳解决方案。例如,最近的结果表明,对于查找相关的Stack Overflow帖子,调优的SVM表现与深度学习器相似,但训练速度显著更快。本文扩展了这一最新结果,通过对数据集进行聚类,然后调优每个聚类内的学习器。这种方法比深度学习快500倍以上(如果使用标准笔记本电脑上的所有核心,则快900倍以上)。重要的是,这种更快的方法生成的分类器几乎与慢得多的深度学习方法一样好(F1分数相差不到2%)。因此,我们推荐这种更快的方法,因为它更容易复现且使用的CPU资源少得多。更一般地,我们建议研究者在发布研究结果之前,将他们所谓复杂的方法与更简单的替代方案(例如应用更简单的学习器来构建局部模型)进行比较。

英文摘要:

Deep learning methods are useful for high-dimensional data and are becoming widely used in many areas of software engineering. Deep learners utilizes extensive computational power and can take a long time to train-- making it difficult to widely validate and repeat and improve their results. Further, they are not the best solution in all domains. For example, recent results show that for finding related Stack Overflow posts, a tuned SVM performs similarly to a deep learner, but is significantly faster to train. This paper extends that recent result by clustering the dataset, then tuning very learners within each cluster. This approach is over 500 times faster than deep learning (and over 900 times faster if we use all the cores on a standard laptop computer). Significantly, this faster approach generates classifiers nearly as good (within 2\% F1 Score) as the much slower deep learning method. Hence we recommend this faster methods since it is much easier to reproduce and utilizes far fewer CPU resources. More generally, we recommend that before researchers release research results, that they compare their supposedly sophisticated methods against simpler alternatives (e.g applying simpler learners to build local 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。

↑