BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search

Abstract

Automatic neural architecture search techniques are becoming increasingly important in machine learning area. Especially, weight sharing methods have shown remarkable potentials on searching good network architectures with few computational resources. However, existing weight sharing methods mainly suffer limitations on searching strategies: these methods either uniformly train all network paths to convergence which introduces conflicts between branches and wastes a large amount of computation on unpromising candidates, or selectively train branches with different frequency which leads to unfair evaluation and comparison among paths. To address these issues, we propose a novel neural architecture search method with balanced training strategy to ensure fair comparisons and a selective drop mechanism to reduce conflicts among candidate paths. The experimental results show that our proposed method can achieve a leading performance of 79.0% on ImageNet under mobile settings, which outperforms other state-of-the-art methods in both accuracy and efficiency.

References in corpus (5)

• Neural Architecture Search with Reinforcement Learning
• Searching for Activation Functions
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
• Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

Cited by in corpus (3)

• Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
• K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
• Prioritized Architecture Sampling with Monto-Carlo Tree Search