Differentiable neural architecture search (DNAS) is known for its capacity in the automatic generation of superior neural networks. However, DNAS based methods suffer from memory usage explosion when the search space expands, which may prevent them from running successfully on even advanced GPU platforms. On the other hand, reinforcement learning (RL) based methods, while being memory efficient, are extremely time-consuming. Combining the advantages of both types of methods, this paper presents RADARS, a scalable RL-aided DNAS framework that can explore large search spaces in a fast and memory-efficient manner. RADARS iteratively applies RL to prune undesired architecture candidates and identifies a promising subspace to carry out DNAS. Experiments using a workstation with 12 GB GPU memory show that on CIFAR-10 and ImageNet datasets, RADARS can achieve up to 3.41% higher accuracy with 2.5X search time reduction compared with a state-of-the-art RL-based method, while the two DNAS baselines cannot complete due to excessive memory usage or search time. To the best of the authors' knowledge, this is the first DNAS framework that can handle large search spaces with bounded memory usage.
翻译:已知有差异的神经结构搜索(DNAS)是因其在自动生成高级神经网络方面的能力而已知的,但是,基于DNAS的方法在搜索空间扩展时会发生记忆使用爆炸,这可能会妨碍它们成功运行甚至先进的GPU平台。另一方面,基于强化学习(RL)的方法虽然具有记忆效率,但非常耗时。结合这两种方法的优势,本文件展示了RADARRS,这是一个可伸缩的RL辅助DNAS框架,可以快速和记忆高效地探索大型搜索空间。RADARS将RL迭代用RL应用于开发不理想的建筑候选人,并确定了执行DNAS的有希望的子空间。使用12GBGPU记忆存储工作站进行的实验表明,在CIFAR-10和图像网络数据集上,RADRS可以达到3.41%的更高精度,而2.5X搜索时间缩短,而以最新技术RL为基础的方法为基准,而DNAS的两个基线由于过度的记忆使用或搜索时间而无法完成。