As deep learning models become popular, there is a lot of need for deploying them to diverse device environments. Because it is costly to develop and optimize a neural network for every single environment, there is a line of research to search neural networks for multiple target environments efficiently. However, existing works for such a situation still suffer from requiring many GPUs and expensive costs. Motivated by this, we propose a novel neural network optimization framework named Bespoke for low-cost deployment. Our framework searches for a lightweight model by replacing parts of an original model with randomly selected alternatives, each of which comes from a pretrained neural network or the original model. In the practical sense, Bespoke has two significant merits. One is that it requires near zero cost for designing the search space of neural networks. The other merit is that it exploits the sub-networks of public pretrained neural networks, so the total cost is minimal compared to the existing works. We conduct experiments exploring Bespoke's the merits, and the results show that it finds efficient models for multiple targets with meager cost.

翻译：随着深度学习模型日益普及，将其部署到多样化的设备环境中需求巨大。由于为每个环境单独开发和优化神经网络成本高昂，学界出现了一系列研究，旨在为多个目标环境高效地搜索神经网络。然而，现有应对此类场景的工作仍需消耗大量GPU且成本昂贵。受此启发，我们提出了一种名为Bespoke的新型神经网络优化框架，用于低成本部署。该框架通过将原始模型的部分模块替换为随机选择的备选模块（每个备选模块来自预训练神经网络或原始模型本身）来搜索轻量级模型。在实际应用中，Bespoke具有两大显著优势：其一，它几乎无需设计神经网络搜索空间的成本；其二，它充分利用公开预训练神经网络的子网络，因此相比现有工作，总成本极低。我们通过实验探索了Bespoke的优越性，结果表明，该框架能以极低的成本为多个目标找到高效模型。