Knowledge Distillation (KD) has recently emerged as a popular method for compressing neural networks. In recent studies, generalized distillation methods that find parameters and architectures of student models at the same time have been proposed. Still, this search method requires a lot of computation to search for architectures and has the disadvantage of considering only convolutional blocks in their search space. This paper introduces a new algorithm, coined as Trust Region Aware architecture search to Distill knowledge Effectively (TRADE), that rapidly finds effective student architectures from several state-of-the-art architectures using trust region Bayesian optimization approach. Experimental results show our proposed TRADE algorithm consistently outperforms both the conventional NAS approach and pre-defined architecture under KD training.
翻译:知识蒸馏(KD)最近成为压缩神经网络的流行方法。在最近的研究中,提出了同时寻找学生模型参数和结构的通用蒸馏方法。不过,这一搜索方法需要大量计算来搜索建筑,其缺点是只考虑搜索空间中的革命区块。本文引入了一种新的算法,称为“信任区域认知建筑搜索以有效提炼知识”(TRADE),它迅速发现一些使用巴耶西亚地区最佳化方法的最新建筑中的学生结构。实验结果显示,我们拟议的贸易算法一贯优于传统的NAS方法和KD培训中预先确定的架构。