A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS
Abstract
This work proposes a novel Graph-based neural ArchiTecture Encoding Scheme, a.k.a. GATES, to improve the predictor-based neural architecture search. Specifically, different from existing graph-based schemes, GATES models the operations as the transformation of the propagating information, which mimics the actual data processing of neural architecture. GATES is a more reasonable modeling of the neural architectures, and can encode architectures from both the ""operation on node"" and ""operation on edge"" cell search spaces consistently. Experimental results on various search spaces confirm GATES's effectiveness in improving the performance predictor. Furthermore, equipped with the improved performance predictor, the sample efficiency of the predictor-based neural architecture search (NAS) flow is boosted.
Cite
Text
Ning et al. "A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58601-0_12Markdown
[Ning et al. "A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/ning2020eccv-generic/) doi:10.1007/978-3-030-58601-0_12BibTeX
@inproceedings{ning2020eccv-generic,
title = {{A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS}},
author = {Ning, Xuefei and Zheng, Yin and Zhao, Tianchen and Wang, Yu and Yang, Huazhong},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58601-0_12},
url = {https://mlanthology.org/eccv/2020/ning2020eccv-generic/}
}