Unchain the Search Space with Hierarchical Differentiable Architecture Search
This work addresses the limitation of restricted search spaces in Differentiable Architecture Search (DAS) for researchers and practitioners aiming to achieve higher-performing neural network architectures.
This paper proposes Hierarchical Differentiable Architecture Search (H-DAS) to expand the search space beyond repeatable cell structures, enabling architecture search at both cell and stage levels. This approach allows for stage-specific cell structures and optimizes inter-cell connections, leading to improved network performance on CIFAR10 and ImageNet without significant cost increases.
Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly focus on searching for a repeatable cell structure, which is then stacked sequentially in multiple stages to form the networks. This configuration significantly reduces the search space, and ignores the importance of connections between the cells. To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level and at the stage level. Specifically, the cell-level search space is relaxed so that the networks can learn stage-specific cell structures. For the stage-level search, we systematically study the architectures of stages, including the number of cells in each stage and the connections between the cells. Based on insightful observations, we design several search rules and losses, and mange to search for better stage-level architectures. Such hierarchical search space greatly improves the performance of the networks without introducing expensive search cost. Extensive experiments on CIFAR10 and ImageNet demonstrate the effectiveness of the proposed H-DAS. Moreover, the searched stage-level architectures can be combined with the cell structures searched by existing DAS methods to further boost the performance. Code is available at: https://github.com/MalongTech/research-HDAS