Corpus ID: 219636245

Few-shot Neural Architecture Search

@article{Zhao2020FewshotNA,
  title={Few-shot Neural Architecture Search},
  author={Yiyang Zhao and Linnan Wang and Yuandong Tian and Rodrigo Fonseca and Tian Guo},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.06863}
}

Yiyang Zhao, Linnan Wang, +2 authors Tian Guo

Published 2020

Computer Science

ArXiv

To improve the search efficiency for Neural Architecture Search (NAS), One-shot NAS proposes to train a single super-net to approximate the performance of proposal architectures during search via weight-sharing. While this greatly reduces the computation cost, due to approximation error, the performance prediction by a single super-net is less accurate than training each proposal architecture from scratch, leading to search inefficiency. In this work, we propose few-shot NAS that explores the… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed