BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search

Automatic neural architecture search techniques are becoming increasingly important in machine learning area. Especially, weight sharing methods have shown remarkable potentials on searching good network architectures with few computational resources. However, existing weight sharing methods mainly...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-12
Main Authors: Fang, Muyuan, Wang, Qiang, Zhao, Zhong
Format: Article
Language:English
Subjects:
Architecture
Machine learning
Searching
Training
Weight
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatic neural architecture search techniques are becoming increasingly important in machine learning area. Especially, weight sharing methods have shown remarkable potentials on searching good network architectures with few computational resources. However, existing weight sharing methods mainly suffer limitations on searching strategies: these methods either uniformly train all network paths to convergence which introduces conflicts between branches and wastes a large amount of computation on unpromising candidates, or selectively train branches with different frequency which leads to unfair evaluation and comparison among paths. To address these issues, we propose a novel neural architecture search method with balanced training strategy to ensure fair comparisons and a selective drop mechanism to reduce conflicts among candidate paths. The experimental results show that our proposed method can achieve a leading performance of 79.0% on ImageNet under mobile settings, which outperforms other state-of-the-art methods in both accuracy and efficiency.
ISSN:2331-8422