DeepAI AI Chat
Log In Sign Up

CARS: Continuous Evolution for Efficient Neural Architecture Search

by   Zhaohui Yang, et al.
HUAWEI Technologies Co., Ltd.
Peking University

Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for searching neural networks. Architectures in the population which share parameters within one supernet in the latest iteration will be tuned over the training dataset with a few epochs. The searching in the next evolution iteration will directly inherit both the supernet and the population, which accelerates the optimal network generation. The non-dominated sorting strategy is further applied to preserve only results on the Pareto front for accurately updating the supernet. Several neural networks with different model sizes and performance will be produced after the continuous search with only 0.4 GPU days. As a result, our framework provides a series of networks with the number of parameters ranging from 3.7M to 5.1M under mobile settings. These networks surpass those produced by the state-of-the-art methods on the benchmark ImageNet dataset.


page 1

page 2

page 3

page 4


EENA: Efficient Evolution of Neural Architecture

Latest algorithms for automatic neural architecture search perform remar...

Differentiable Neural Architecture Learning for Efficient Neural Network Design

Automated neural network design has received ever-increasing attention w...

MoGA: Searching Beyond MobileNetV3

The evolution of MobileNets has laid a solid foundation for neural netwo...

Rethinking Performance Estimation in Neural Architecture Search

Neural architecture search (NAS) remains a challenging problem, which is...

FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation

We present FMAS, a fast multi-objective neural architecture search frame...

Probeable DARTS with Application to Computational Pathology

AI technology has made remarkable achievements in computational patholog...

Analysis of Expected Hitting Time for Designing Evolutionary Neural Architecture Search Algorithms

Evolutionary computation-based neural architecture search (ENAS) is a po...

Code Repositories


Pytorch code for paper: CARS: Continuous Evolution for Efficient Neural Architecture Search

view repo