IRLAS: Inverse Reinforcement Learning for Architecture Search

Abstract

In this paper, we propose an inverse reinforcement learning method for architecture search (IRLAS), which trains an agent to learn to search network structures that are topologically inspired by human-designed network. Most existing architecture search approaches totally neglect the topological characteristics of architectures, which results in complicated architecture with a high inference latency. Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt). To avoid raising a too strong prior over the search space, we introduce inverse reinforcement learning to train the mirror stimuli function and exploit it as a heuristic guidance for architecture search, easily generalized to different architecture search algorithms. On CIFAR-10, the best architecture searched by our proposed IRLAS achieves 2.60% error rate. For ImageNet mobile setting, our model achieves a state-of-the-art top-1 accuracy 75.28%, while being 2~4x faster than most auto-generated architectures. A fast version of this model achieves 10% faster than MobileNetV2, while maintaining a higher accuracy.

References in corpus (9)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• Wide Residual Networks
• Efficient Neural Architecture Search via Parameter Sharing
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Efficient Architecture Search by Network Transformation
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• Convolutional Neural Fabrics

Cited by in corpus (6)

• AM-LFS: AutoML for Loss Function Search
• BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search
• Online Hyper-parameter Learning for Auto-Augmentation Strategy
• Graph-guided Architecture Search for Real-time Semantic Segmentation
• Intra-Ensemble in Neural Networks
• NASIB: Neural Architecture Search withIn Budget