EDNAS: An Efficient Neural Architecture Design based on Distribution Estimation

Zhenyao Zhao, Guang En Zhang, Min Jiang, Liang Feng, Kay Chen Tan

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Neural architecture search (NAS) is the process of automatically searching for the best performing neural model on a given task. Designing a neural model requires a lot of time for experts, NAS's automated process effectively solves this problem and makes neural networks easier to promote. Although NAS has achieved excellent performance, its search process is still very time consuming. In this paper, we propose a neural architecture design method based on distribution estimation method called EDNAS, a fast and economical solution to design neural architecture automatically. In EDNAS, we assume that the best performing architecture obeys a certain probability distribution in search space. Therefore, NAS can be transformed to learning this probability distribution. We construct a probability model on the search space, and search for this probability distribution by iterating the probability model. Finally, an architecture that maximizes the performance on a validation set is generated from this probability distribution. Experiment shows the efficiency of our method. On CIFAR-10 dataset, EDNAS discovers a novel architecture in just 4 hours with 2.89% test error, which shows efficent and strong performance.

Original languageEnglish
Title of host publication2nd International Conference on Industrial Artificial Intelligence, IAI 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
ISBN (Electronic)9781728182162
DOIs
Publication statusPublished - 23 Oct 2020
Externally publishedYes
Event2nd International Conference on Industrial Artificial Intelligence, IAI 2020 - Shenyang, China
Duration: 23 Oct 202025 Oct 2020

Publication series

Name2nd International Conference on Industrial Artificial Intelligence, IAI 2020

Conference

Conference2nd International Conference on Industrial Artificial Intelligence, IAI 2020
Country/TerritoryChina
CityShenyang
Period23/10/2025/10/20

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Industrial and Manufacturing Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'EDNAS: An Efficient Neural Architecture Design based on Distribution Estimation'. Together they form a unique fingerprint.

Cite this