Neural Architecture Search (NAS) can automatically design well-performed architectures of Deep Neural Networks (DNNs) for the tasks at hand. However, one bottleneck of NAS is the prohibitively computational cost largely due to the expensive performance evaluation. The neural predictors can directly estimate the performance without any training of the DNNs to be evaluated, thus have drawn increasing attention from researchers. Despite their popularity, they also suffer a severe limitation: the shortage of annotated DNN architectures for effectively training the neural predictors. In this paper, we proposed Homogeneous Architecture Augmentation for Neural Predictor (HAAP) of DNN architectures to address the issue aforementioned. Specifically, a homogeneous architecture augmentation algorithm is proposed in HAAP to generate sufficient training data taking the use of homogeneous representation. Furthermore, the one-hot encoding strategy is introduced into HAAP to make the representation of DNN architectures more effective. The experiments have been conducted on both NAS-Benchmark-101 and NAS-Bench-201 dataset. The experimental results demonstrate that the proposed HAAP algorithm outperforms the state of the arts compared, yet with much less training data. In addition, the ablation studies on both benchmark datasets have also shown the universality of the homogeneous architecture augmentation.
翻译:神经结构搜索(NAS)可以自动设计完成当前任务的深神经网络(DNNS)的完善结构。 但是,NAS的一个瓶颈是令人望而却步的计算成本,主要因为业绩评估费用昂贵。神经预测器可以直接估计性能,而不对DNS进行任何培训,从而引起研究人员越来越多的注意。尽管他们受到欢迎,但他们也受到严重限制:缺少一个附加注释的DNNS结构,以有效培训神经预测器。在本文中,我们建议DNNS结构神经预测器(HAAP)的智能结构增强(HAAP)解决上述问题。具体地说,HAAP提出了一种同质结构增强算法,以利用同质代表制生成足够的培训数据。此外,HAAP引入了一热编码战略,以使DNNE结构的表述更加有效。在NAS-Benchmark-101和NAS-Bench-201数据集方面都进行了实验。实验结果显示,拟议的HAAP算法的系统结构结构比标准化数据都比标准化数据更低。