GOLD-NAS: Gradual, One-Level, Differentiable

Abstract

There has been a large literature of 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 $10^{160}$ 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. We believe the new space and search algorithm can advance the search of differentiable NAS.

14 pages, 5 figures

References in corpus (16)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Improved Regularization of Convolutional Neural Networks with Cutout
• DARTS: Differentiable Architecture Search
• AutoAugment: Learning Augmentation Policies from Data
• Large-Scale Evolution of Image Classifiers
• Neural Architecture Optimization
• Efficient Architecture Search by Network Transformation
• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
• SNAS: Stochastic Neural Architecture Search
• DARTS+: Improved Differentiable Architecture Search with Early Stopping
• Random Search and Reproducibility for Neural Architecture Search
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
• Latency-Aware Differentiable Neural Architecture Search
• XNAS: Neural Architecture Search with Expert Advice
• Hierarchical Neural Architecture Search via Operator Clustering

Cited by in corpus (9)

• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• SparseBERT: Rethinking the Importance Analysis in Self-attention
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
• Effective, Efficient and Robust Neural Architecture Search
• Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
• Single-level Optimization For Differential Architecture Search
• iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization
• Neural Architecture Search as Sparse Supernet
• Single-DARTS: Towards Stable Architecture Search