Reinforced Evolutionary Neural Architecture Search

TL;DR

This paper introduces RE- NAS, a reinforcement-guided evolutionary method for neural architecture search that efficiently discovers high-performance models with limited computational resources, achieving state-of-the-art results on CIFAR-10, ImageNet, and PASCAL VOC.

Contribution

The paper presents a novel reinforced mutation controller integrated into evolutionary NAS, enabling efficient architecture exploration with minimal resource use.

Findings

RENASNet achieves 75.7% top-1 accuracy on ImageNet.

RENASNet outperforms MobileNet-v1, MobileNet-v2, and NASNet in semantic segmentation.

The method requires limited computational resources due to parameter inheritance.

Abstract

Neural Architecture Search (NAS) is an important yet challenging task in network design due to its high computational consumption. To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is an evolutionary method with the reinforced mutation for NAS. Our method integrates reinforced mutation into an evolution algorithm for neural architecture exploration, in which a mutation controller is introduced to learn the effects of slight modifications and make mutation actions. The reinforced mutation controller guides the model population to evolve efficiently. Furthermore, as child models can inherit parameters from their parents during evolution, our method requires very limited computational resources. In experiments, we conduct the proposed search method on CIFAR-10 and obtain a powerful network architecture, RENASNet. This architecture achieves a competitive result on CIFAR-10. The explored network architecture is transferable to ImageNet and achieves a new state-of-the-art accuracy, i.e., 75.7% top-1 accuracy with 5.36M parameters on mobile ImageNet. We further test its performance on semantic segmentation with DeepLabv3 on the PASCAL VOC. RENASNet outperforms MobileNet-v1, MobileNet-v2 and NASNet. It achieves 75.83% mIOU without being pre-trained on COCO.