GOLD-NAS: Gradual, One-Level, Differentiable

Kaifeng Bi, Lingxi Xie, Xin Chen, Longhui Wei, Qi Tian

Keywords: Neural Architecture Search, GOLD-NAS

Abstract: There has been a large literature on neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper, we first relax these manually designed constraints and enlarge the search space to contain more than $10^{117}$ candidates. In the new space, most existing differentiable search methods can fail dramatically. We then propose a novel algorithm named Gradual One-Level Differentiable Neural Architecture Search (GOLD-NAS) which introduces a variable resource constraint to one-level optimization so that the weak operators are gradually pruned out from the super-network. In standard image classification benchmarks, GOLD-NAS can find a series of Pareto-optimal architectures within a single search procedure. Most of the discovered architectures were never studied before, yet they achieve a nice tradeoff between recognition accuracy and model complexity. GOLD-NAS also shows generalization ability in extended search spaces with different candidate operators.

One-sentence Summary: A new differentiable NAS framework incorporating one-level optimization and gradual pruning, working on large search spaces

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2007.03331/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=mxz-fcGaqb