Bespoke: A Block-Level Neural Network Optimization Framework for Low-Cost Deployment
This addresses the need for low-cost neural network optimization for deployment across various environments, though it appears incremental as it builds on existing search methods.
The paper tackles the problem of costly deployment of deep learning models to diverse devices by proposing Bespoke, a framework that searches for lightweight models by replacing parts of an original model with alternatives from pretrained networks, achieving efficient models for multiple targets with minimal cost.
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.