Roulette: A Pruning Framework to Train a Sparse Neural Network From Scratch
Authors:
Open Access
- 10 March 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 51134-51145
Abstract
Due to space and inference time restrictions, finding an efficient and sparse sub-network from a dense and over-parameterized network is critical for deploying neural networks on edge devices. Recent efforts explore obtaining a sparse sub-network by performing network pruning during training procedures to reduce training costs, such as memory and floating-point operations (FLOPs). However, these works take more than 1.4× the total number of iterations and try all possible pruning parameters manually to obtain sparse sub-networks. In this paper, we present a pruning framework Roulette to train a sparse network from scratch. First, we propose a novel method to train a sparse network by Pruning through the lens of Loss Landscape iteratively and automatically (PLL). We do a theoretical analysis that the curvature of the loss function is higher in the initial phase and can conduct us to start network pruning. According to our results on CIFAR-10/100 and ImageNet dataset, PLL saves up to 4× training FLOPs than prior works while maintaining comparable or even better accuracy. Then we design push and pull operations to synchronize the pruned weights on different GPUs during training, scaling PLL to multiple GPUs linearly. To our knowledge, Roulette is the first network pruning framework supporting multiple GPUs linearly.Keywords
Funding Information
- Strategic Priority Research Program of Chinese Academy of Sciences (XDA19020400)
This publication has 23 references indexed in Scilit:
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression2017
- Learning Efficient Convolutional Networks through Network Slimming2017
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- More is Less: A More Complicated Network with Less Inference Complexity2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- EIEACM SIGARCH Computer Architecture News, 2016
- Deep Residual Learning for Image Recognition2016
- Going deeper with convolutions2015
- HPC Programming on Intel Many-Integrated-Core Hardware with MAGMA Port to Xeon PhiScientific Programming, 2015
- Long Short-Term MemoryNeural Computation, 1997