arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.13396cs.LGcs.AIstat.ML
收藏

NAS-Bench-Suite:NAS评估(现在)非常简单

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

University of Freiburg(弗莱堡大学);Bosch Center for AI(博世人工智能中心)

Yash Mehta, Colin White, Arber Zela, Arjun Krishnakumar, Guri Zabergja, Shakiba Moradian, Mahmoud Safari, Kaicheng Yu, Frank Hutter

摘要:

NAS-Bench-101和NAS-Bench-201等表格基准的发布显著降低了在神经架构搜索(NAS)中进行科学研究的计算开销。虽然它们已被广泛采用并用于调整现实世界的NAS算法,但这些基准测试仅限于小搜索空间,并且仅关注图像分类。最近,已经引入了几个新的NAS基准测试,这些测试覆盖了广泛任务的更大搜索空间,包括目标检测、语音识别和自然语言处理。然而,到目前为止,这些NAS基准之间的巨大差异阻碍了它们的广泛采用,限制了研究人员只能使用少数基准。在这项工作中,我们提出了一个深入的分析流行的NAS算法和性能预测方法在25个不同的组合的搜索空间和数据集,发现许多结论得出的一些NAS基准不推广到其他基准。为了帮助解决这个问题,我们引入了NAS-Bench-Suite,这是一个全面且可扩展的NAS基准测试集合,可通过统一的界面访问,旨在促进可重现,可推广和快速的NAS研究。我们的代码可在https://github.com/automl/naslib上获得。

英文摘要:

The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has significantly lowered the computational overhead for conducting scientific research in neural architecture search (NAS). Although they have been widely adopted and used to tune real-world NAS algorithms, these benchmarks are limited to small search spaces and focus solely on image classification. Recently, several new NAS benchmarks have been introduced that cover significantly larger search spaces over a wide range of tasks, including object detection, speech recognition, and natural language processing. However, substantial differences among these NAS benchmarks have so far prevented their widespread adoption, limiting researchers to using just a few benchmarks. In this work, we present an in-depth analysis of popular NAS algorithms and performance prediction methods across 25 different combinations of search spaces and datasets, finding that many conclusions drawn from a few NAS benchmarks do not generalize to other benchmarks. To help remedy this problem, we introduce NAS-Bench-Suite, a comprehensive and extensible collection of NAS benchmarks, accessible through a unified interface, created with the aim to facilitate reproducible, generalizable, and rapid NAS research. Our code is available at https://github.com/automl/naslib.

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。

↑