Article
Version 1
Preserved in Portico This version is not peer-reviewed
FTSO: Effective NAS via First Topology Second Operator
Version 1
: Received: 17 March 2023 / Approved: 20 March 2023 / Online: 20 March 2023 (06:08:35 CET)
Version 2 : Received: 28 March 2023 / Approved: 29 March 2023 / Online: 29 March 2023 (02:14:14 CEST)
Version 2 : Received: 28 March 2023 / Approved: 29 March 2023 / Online: 29 March 2023 (02:14:14 CEST)
How to cite: Wang, L.; Chen, L. FTSO: Effective NAS via First Topology Second Operator. Preprints 2023, 2023030345. https://doi.org/10.20944/preprints202303.0345.v1 Wang, L.; Chen, L. FTSO: Effective NAS via First Topology Second Operator. Preprints 2023, 2023030345. https://doi.org/10.20944/preprints202303.0345.v1
Abstract
Existing one-shot neural architecture search (NAS) methods have to conduct a search over a giant super-net, which leads to the huge computational cost. To reduce such cost, in this paper, we propose a method, called FTSO, to divide the whole architecture search into two sub-steps. Specifically, in the first step, we only search for the topology, and in the second step, we search for the operators. FTSO not only reduces NAS’s search time from days to 0.68 seconds, but also significantly improves the found architecture's accuracy. Our extensive experiments on ImageNet show that within 18 seconds, FTSO can achieve a 76.4% testing accuracy, 1.5% higher than the SOTA, PC-DARTS. In addition, FTSO can reach a 97.77% testing accuracy, 0.27% higher than the SOTA, with nearly 100% (99.8%) search time saved, when searching on CIFAR10.
Keywords
neural architecture search; machine learning; computer vision
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
