English

Neural Architecture Search as Sparse Supernet

Computer Vision and Pattern Recognition 2021-04-01 v2 Machine Learning

Abstract

This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse supernet, we exploit a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework. Extensive experiments on Convolutional Neural Network and Recurrent Neural Network search demonstrate that the proposed method is capable of searching for compact, general and powerful neural architectures.

Keywords

Cite

@article{arxiv.2007.16112,
  title  = {Neural Architecture Search as Sparse Supernet},
  author = {Yan Wu and Aoming Liu and Zhiwu Huang and Siwei Zhang and Luc Van Gool},
  journal= {arXiv preprint arXiv:2007.16112},
  year   = {2021}
}

Comments

Accepted to AAAI 2021

R2 v1 2026-06-23T17:33:30.487Z