Reinforced Evolutionary Neural Architecture Search

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.

References in corpus (9)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• DARTS: Differentiable Architecture Search
• Large-Scale Evolution of Image Classifiers
• Designing Neural Network Architectures using Reinforcement Learning
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Efficient Architecture Search by Network Transformation

Cited by in corpus (12)

• AutoML: A Survey of the State-of-the-Art
• A Survey on Evolutionary Neural Architecture Search
• NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
• Auto-GNN: Neural Architecture Search of Graph Neural Networks
• Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
• Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
• Evolutionary-Neural Hybrid Agents for Architecture Search
• PV-NAS: Practical Neural Architecture Search for Video Recognition
• Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
• Graph-guided Architecture Search for Real-time Semantic Segmentation
• NASIB: Neural Architecture Search withIn Budget
• Efficient Neural Architecture Search with Performance Prediction