Joint Neural Architecture Search and Quantization

Abstract

Designing neural architectures is a fundamental step in deep learning applications. As a partner technique, model compression on neural networks has been widely investigated to gear the needs that the deep learning algorithms could be run with the limited computation resources on mobile devices. Currently, both the tasks of architecture design and model compression require expertise tricks and tedious trials. In this paper, we integrate these two tasks into one unified framework, which enables the joint architecture search with quantization (compression) policies for neural networks. This method is named JASQ. Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices. Technically, a multi-objective evolutionary search algorithm is introduced to search the models under the balance between model size and performance accuracy. In experiments, we find that our approach outperforms the methods that search only for architectures or only for quantization policies. 1) Specifically, given existing networks, our approach can provide them with learning-based quantization policies, and outperforms their 2 bits, 4 bits, 8 bits, and 16 bits counterparts. It can yield higher accuracies than the float models, for example, over 1.02% higher accuracy on MobileNet-v1. 2) What is more, under the balance between model size and performance accuracy, two models are obtained with joint search of architectures and quantization policies: a high-accuracy model and a small model, JASQNet and JASQNet-Small that achieves 2.97% error rate with 0.9 MB on CIFAR-10.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• Do Deep Nets Really Need to be Deep?
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• DARTS: Differentiable Architecture Search
• Trained Ternary Quantization
• Model compression via distillation and quantization
• WRPN: Wide Reduced-Precision Networks
• DeepArchitect: Automatically Designing and Training Deep Architectures
• Effective Quantization Methods for Recurrent Neural Networks

Cited by in corpus (10)

• A Survey on Evolutionary Neural Architecture Search
• FasterSeg: Searching for Faster Real-time Semantic Segmentation
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer
• Learning Architectures for Binary Networks
• Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks
• Training Quantized Neural Networks with a Full-precision Auxiliary Module
• BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements
• Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
• InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks