Neural Architecture Search as Sparse Supernet
METADATA ONLY
Loading...
Author / Producer
Date
2021-05-28
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
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.
Permanent link
Publication status
published
Editor
Book title
Volume
35 (12)
Pages / Article No.
10379 - 10387
Publisher
AAAI
Event
35th AAAI Conference on Artificial Intelligence (AAAI 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Transfer; Adaptation; Multi-task; Meta; Automated learning