Early methods in the rapidly developing field of neural architecture search (NAS) required fully training thousands of neural networks. To reduce this extreme computational cost, dozens of techniques have since been proposed to predict the final performance of neural architectures. Despite the success of such performance prediction methods, it is not well-understood how different families of techniques compare to one another, due to the lack of an agreed-upon evaluation metric and optimization for different constraints on the initialization time and query time. In this work, we give the first large-scale study of performance predictors by analyzing 31 techniques ranging from learning curve extrapolation, to weight-sharing, to supervised learning, to "zero-cost" proxies. We test a number of correlation- and rank-based performance measures in a variety of settings, as well as the ability of each technique to speed up predictor-based NAS frameworks. Our results act as recommendations for the best predictors to use in different settings, and we show that certain families of predictors can be combined to achieve even better predictive power, opening up promising research directions. Our code, featuring a library of 31 performance predictors, is available at https://github.com/automl/naslib.
翻译:在迅速开发的神经结构搜索(NAS)领域,早期方法要求充分培训数千个神经网络。为了降低这一极端计算成本,此后提出了数十种技术来预测神经结构的最终性能。尽管这种性能预测方法取得了成功,但人们并不十分了解,由于缺乏商定的评价指标和最佳方法,对启动时间和查询时间的不同限制缺乏不同的评估指标和优化。在这项工作中,我们通过分析31种技术对性能预测器进行了首次大规模研究,这些技术包括学习曲线外推法、权重共享、受监督的学习、“零成本”代号等。我们测试了各种环境中的一些相关性能和级性能计量,以及每种技术加速预测基于性能的NAS框架的能力。我们的结果为最佳预测器在不同环境中使用提供了建议。我们显示,某些预测器的家属可以结合在一起,以达到更好的预测力,打开有希望的研究方向。我们的代码,由31个性能预测仪库组成,可在 http://gius/gistrabcom.