Neural architecture search as sparse supernet

Y. WU, A. LIU, Zhiwu HUANG, S. ZHANG, Gool L. VAN, Alan Z Liu

Research output: Contribution to journalArticlepeer-review

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.

Original languageAmerican English
JournalThe Proceedings of 35th AAAI Conference on Artificial Intelligence, 2021 Feb 2-9
StatePublished - Feb 1 2021

Disciplines

  • OS and Networks
  • Systems Architecture

Cite this