Sample-Efficient Neural Architecture Search by Learning Action Space

TL;DR

This paper introduces LaNAS, a neural architecture search method that learns action spaces to improve sample efficiency, achieving state-of-the-art results with significantly fewer samples than existing methods.

Contribution

LaNAS learns actions to partition the search space, significantly improving sample efficiency in NAS compared to traditional MCTS approaches.

Findings

LaNAS is at least 10 times more sample efficient than baseline methods.

Achieves 99.0% accuracy on CIFAR-10 with only 800 samples.

Outperforms existing NAS methods on ImageNet with fewer samples.

Abstract

Neural Architecture Search (NAS) has emerged as a promising technique for automatic neural network design. However, existing MCTS based NAS approaches often utilize manually designed action space, which is not directly related to the performance metric to be optimized (e.g., accuracy), leading to sample-inefficient explorations of architectures. To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics. During the search phase, as different action sequences lead to regions with different performance, the search efficiency can be significantly improved by biasing towards the good regions. On three NAS tasks, empirical results demonstrate that LaNAS is at least an order more sample efficient than baseline methods including evolutionary algorithms, Bayesian optimizations, and random search. When applied in practice, both one-shot and regular LaNAS consistently outperform existing results. Particularly, LaNAS achieves 99.0% accuracy on CIFAR-10 and 80.8% top1 accuracy at 600 MFLOPS on ImageNet in only 800 samples, significantly outperforming AmoebaNet with 33x fewer samples. Our code is publicly available at https://github.com/facebookresearch/LaMCTS.