Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search

TL;DR

This paper introduces Curriculum Neural Architecture Search (CNAS), a method that gradually enlarges the search space to efficiently find better neural network architectures, overcoming the challenge of space explosion in NAS.

Contribution

The paper proposes a curriculum search strategy for NAS that incrementally explores larger search spaces, improving efficiency and architecture quality.

Findings

CNAS outperforms existing NAS methods in search efficiency.

The method achieves better architectures on CIFAR-10 and ImageNet.

Significant reduction in search space exploration time.

Abstract

Neural architecture search (NAS) has become an important approach to automatically find effective architectures. To cover all possible good architectures, we need to search in an extremely large search space with billions of candidate architectures. More critically, given a large search space, we may face a very challenging issue of space explosion. However, due to the limitation of computational resources, we can only sample a very small proportion of the architectures, which provides insufficient information for the training. As a result, existing methods may often produce suboptimal architectures. To alleviate this issue, we propose a curriculum search method that starts from a small search space and gradually incorporates the learned knowledge to guide the search in a large space. With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method significantly improves the search efficiency and finds better architectures than existing NAS methods. Extensive experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of the proposed method.