Neural Architecture Search as Sparse Supernet

TL;DR

This paper introduces a novel approach to Neural Architecture Search by modeling it as a sparse supernet with a continuous architecture representation, enabling automatic mixed-path architecture optimization.

Contribution

It proposes a new sparse supernet model with a continuous architecture representation and a hierarchical optimization algorithm for efficient NAS.

Findings

Successfully searches for compact neural architectures.

Demonstrates effectiveness on CNN and RNN search tasks.

Achieves general and powerful architectures.

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.