Neural Architecture Search using Property Guided Synthesis

Abstract

In the past few years, neural architecture search (NAS) has become an increasingly important tool within the deep learning community. Despite the many recent successes of NAS, however, most existing approaches operate within highly structured design spaces, and hence explore only a small fraction of the full search space of neural architectures while also requiring significant manual effort from domain experts. In this work, we develop techniques that enable efficient NAS in a significantly larger design space. To accomplish this, we propose to perform NAS in an abstract search space of program properties. Our key insights are as follows: (1) the abstract search space is significantly smaller than the original search space, and (2) architectures with similar program properties also have similar performance; thus, we can search more efficiently in the abstract search space. To enable this approach, we also propose a novel efficient synthesis procedure, which accepts a set of promising program properties, and returns a satisfying neural architecture. We implement our approach, $\alpha$NAS, within an evolutionary framework, where the mutations are guided by the program properties. Starting with a ResNet-34 model, $\alpha$NAS produces a model with slightly improved accuracy on CIFAR-10 but 96% fewer parameters. On ImageNet, $\alpha$NAS is able to improve over Vision Transformer (30% fewer FLOPS and parameters), ResNet-50 (23% fewer FLOPS, 14% fewer parameters), and EfficientNet (7% fewer FLOPS and parameters) without any degradation in accuracy.

arXiv commentOur code is available at https://github.com/google-research/google-research/tree/master/abstract_nas

References in corpus (11)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Neural Architecture Search with Reinforcement Learning
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• EfficientNetV2: Smaller Models and Faster Training
• Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
• Scalable Methods for 8-bit Training of Neural Networks
• Evaluating the Search Phase of Neural Architecture Search
• Beyond Data and Model Parallelism for Deep Neural Networks
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
• Equality Saturation for Tensor Graph Superoptimization

Cited by in corpus (1)

• Syno: Structured Synthesis for Neural Operators