SOTAVerified

When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

2022-04-11Code Available0· sign in to hype

Guocheng Qian, Xuanyang Zhang, Guohao Li, Chen Zhao, Yukang Chen, Xiangyu Zhang, Bernard Ghanem, Jian Sun

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which improves search efficiency by exploring only a small number of architectures while also achieving a higher search accuracy. TNAS introduces an architecture tree and a binary operation tree, to factorize the search space and substantially reduce the exploration size. TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture. Impressively, TNAS finds the global optimal architecture on CIFAR-10 with test accuracy of 94.37\% in four GPU hours in NAS-Bench-201. The average test accuracy is 94.35\%, which outperforms the state-of-the-art. Code is available at: https://github.com/guochengqian/TNAS.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
NAS-Bench-201, CIFAR-10TNASAccuracy (Test)94.35Unverified
NAS-Bench-201, CIFAR-100TNASAccuracy (Test)73.02Unverified
NAS-Bench-201, ImageNet-16-120TNASAccuracy (Test)46.31Unverified

Reproductions