When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

Guocheng Qian, Xuanyang Zhang, Guohao Li, Chen Zhao, Yukang Chen, Xiangyu Zhang, Bernard Ghanem, Jian Sun; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2782-2787

Abstract


The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which improves search efficiency by exploring only a small number of architectures while also achieving a higher search accuracy. TNAS introduces an architecture tree and a binary operation tree, to factorize the search space and substantially reduce the exploration size. TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture. Impressively, TNAS finds the global optimal architecture on CIFAR-10 with test accuracy of 94.37% in four GPU hours in NAS-Bench-201. The average test accuracy is 94.35%, which outperforms the state-of-the-art. Code is available at: https://github.com/guochengqian/TNAS.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Qian_2022_CVPR, author = {Qian, Guocheng and Zhang, Xuanyang and Li, Guohao and Zhao, Chen and Chen, Yukang and Zhang, Xiangyu and Ghanem, Bernard and Sun, Jian}, title = {When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {2782-2787} }