Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks

Abstract

Recently, deep learning has become a de facto standard in machine learning with convolutional neural networks (CNNs) demonstrating spectacular success on a wide variety of tasks. However, CNNs are typically very demanding computationally at inference time. One of the ways to alleviate this burden on certain hardware platforms is quantization relying on the use of low-precision arithmetic representation for the weights and the activations. Another popular method is the pruning of the number of filters in each layer. While mainstream deep learning methods train the neural networks weights while keeping the network architecture fixed, the emerging neural architecture search (NAS) techniques make the latter also amenable to training. In this paper, we formulate optimal arithmetic bit length allocation and neural network pruning as a NAS problem, searching for the configurations satisfying a computational complexity budget while maximizing the accuracy. We use a differentiable search method based on the continuous relaxation of the search space proposed by Liu et al. (arXiv:1806.09055). We show, by grid search, that heterogeneous quantized networks suffer from a high variance which renders the benefit of the search questionable. For pruning, improvement over homogeneous cases is possible, but it is still challenging to find those configurations with the proposed method. The code is publicly available at https://github.com/yochaiz/Slimmable and https://github.com/yochaiz/darts-UNIQ

arXiv commentAccepted to ICML Workshop on AutoML 2019

References in corpus (21)

• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• DARTS: Differentiable Architecture Search
• Binarized Neural Networks
• Bayesian Compression for Deep Learning
• NAS-Bench-101: Towards Reproducible Neural Architecture Search
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
• AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
• ASAP: Architecture Search, Anneal and Prune
• ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
• Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference
• Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
• Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)
• NICE: Noise Injection and Clamping Estimation for Neural Network Quantization
• Training Competitive Binary Neural Networks from Scratch
• Quantization for Rapid Deployment of Deep Neural Networks
• AutoQ: Automated Kernel-Wise Neural Network Quantization
• Regularizing Activation Distribution for Training Binarized Deep Networks
• Joint Neural Architecture Search and Quantization
• Improving Neural Architecture Search Image Classifiers via Ensemble Learning
• Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

Cited by in corpus (1)

• Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization