Skip to content

Latest commit

 

History

68 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Surrogate-based Neural Network Structural Pruning

Supervisor: Oleg Bakhteev, PhD

Link
Paper link
Thesis link
Code link
Slides link

Abstract

The paper investigates the problem of structural pruning in neural networks. Structural pruning is the procedure of removing entire groups of parameters from a neural network, for example, filters in CNNs or skip connections. An appropriate pruning strategy can improve both generalization performance and inference efficiency. The main difficulty of structural pruning is that removing a layer requires removing or consistently modifying all dependent layers, especially across arbitrary or novel architectures.

The proposed method is based on the analysis of the deep learning computation graph and the estimation of the information flow propagated through it. By preserving the local dependency structure of the loss function, the method enables the estimation of the importance of operations in the computation graph in a few-shot setting, i.e., using several forward passes of a data subset through the analyzed model. To demonstrate the effectiveness of the proposed method, we conduct multiple experiments on randomly generated neural networks using the MNIST dataset, showing that our approach outperforms existing pruning methods. Furthermore, our method achieves 60.4% accuracy after pruning 43.9% of the parameters of ResNet-18 on the CIFAR-10 classification task without fine-tuning.

About

Removing groups of weights from a neural network based on the deep learning computation graph analyzing and estimation of information flow transferred through it.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages