EDNAS : An Efficient Neural Architecture Design based on Distribution Estimation

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Title of host publicationThe 2nd International Conference on Industrial Artificial Intelligence (IAI 2020)
PublisherIEEE
ISBN (Electronic)978-1-7281-8216-2
Publication statusPublished - Oct 2020

Publication series

Name2nd International Conference on Industrial Artificial Intelligence, IAI 2020

Conference

Title2nd International Conference on Industrial Artificial Intelligence, IAI 2020
PlaceChina
CityShenyang
Period23 - 25 October 2020

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.

Citation Format(s)

EDNAS : An Efficient Neural Architecture Design based on Distribution Estimation. / Zhao, Zhenyao; Zhang, Guang-En; Jiang, Min; Feng, Liang; Tan, Kay Chen.

The 2nd International Conference on Industrial Artificial Intelligence (IAI 2020). IEEE, 2020. 9262190 (2nd International Conference on Industrial Artificial Intelligence, IAI 2020).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review