REAP: A Method for Pruning Convolutional Neural Networks with Performance Preservation

Koji KAMMA; Toshikazu WADA

doi:10.1587/transinf.2020EDP7049

REAP: A Method for Pruning Convolutional Neural Networks with Performance Preservation

Koji KAMMA, Toshikazu WADA

Full Text Views

0

Cite this

Summary :

This paper presents a pruning method, Reconstruction Error Aware Pruning (REAP), to reduce the redundancy of convolutional neural network models for accelerating their inference. In REAP, we have the following steps: 1) Prune the channels whose outputs are redundant and can be reconstructed from the outputs of other channels in each convolutional layer; 2) Update the weights of the remaining channels by least squares method so as to compensate the error caused by pruning. This is how we compress and accelerate the models that are initially large and slow with little degradation. The ability of REAP to maintain the model performances saves us lots of time and labors for retraining the pruned models. The challenge of REAP is the computational cost for selecting the channels to be pruned. For selecting the channels, we need to solve a huge number of least squares problems. We have developed an efficient algorithm based on biorthogonal system to obtain the solutions of those least squares problems. In the experiments, we show that REAP can conduct pruning with smaller sacrifice of the model performances than several existing methods including the previously state-of-the-art one.

Publication: IEICE TRANSACTIONS on Information Vol.E104-D No.1 pp.194-202

Publication Date: 2021/01/01

Publicized: 2020/10/02

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2020EDP7049

Type of Manuscript: PAPER

Category: Biocybernetics, Neurocomputing

Authors

Koji KAMMA
Wakayama University
Toshikazu WADA
Wakayama University

Keyword

pruning, REAP, biorthogonal system

Cite this

Copy

Koji KAMMA, Toshikazu WADA, "REAP: A Method for Pruning Convolutional Neural Networks with Performance Preservation" in IEICE TRANSACTIONS on Information, vol. E104-D, no. 1, pp. 194-202, January 2021, doi: 10.1587/transinf.2020EDP7049.
Abstract: This paper presents a pruning method, Reconstruction Error Aware Pruning (REAP), to reduce the redundancy of convolutional neural network models for accelerating their inference. In REAP, we have the following steps: 1) Prune the channels whose outputs are redundant and can be reconstructed from the outputs of other channels in each convolutional layer; 2) Update the weights of the remaining channels by least squares method so as to compensate the error caused by pruning. This is how we compress and accelerate the models that are initially large and slow with little degradation. The ability of REAP to maintain the model performances saves us lots of time and labors for retraining the pruned models. The challenge of REAP is the computational cost for selecting the channels to be pruned. For selecting the channels, we need to solve a huge number of least squares problems. We have developed an efficient algorithm based on biorthogonal system to obtain the solutions of those least squares problems. In the experiments, we show that REAP can conduct pruning with smaller sacrifice of the model performances than several existing methods including the previously state-of-the-art one.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7049/_p

Copy

@ARTICLE{e104-d_1_194,
author={Koji KAMMA, Toshikazu WADA, },
journal={IEICE TRANSACTIONS on Information},
title={REAP: A Method for Pruning Convolutional Neural Networks with Performance Preservation},
year={2021},
volume={E104-D},
number={1},
pages={194-202},
abstract={This paper presents a pruning method, Reconstruction Error Aware Pruning (REAP), to reduce the redundancy of convolutional neural network models for accelerating their inference. In REAP, we have the following steps: 1) Prune the channels whose outputs are redundant and can be reconstructed from the outputs of other channels in each convolutional layer; 2) Update the weights of the remaining channels by least squares method so as to compensate the error caused by pruning. This is how we compress and accelerate the models that are initially large and slow with little degradation. The ability of REAP to maintain the model performances saves us lots of time and labors for retraining the pruned models. The challenge of REAP is the computational cost for selecting the channels to be pruned. For selecting the channels, we need to solve a huge number of least squares problems. We have developed an efficient algorithm based on biorthogonal system to obtain the solutions of those least squares problems. In the experiments, we show that REAP can conduct pruning with smaller sacrifice of the model performances than several existing methods including the previously state-of-the-art one.},
keywords={},
doi={10.1587/transinf.2020EDP7049},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - REAP: A Method for Pruning Convolutional Neural Networks with Performance Preservation
T2 - IEICE TRANSACTIONS on Information
SP - 194
EP - 202
AU - Koji KAMMA
AU - Toshikazu WADA
PY - 2021
DO - 10.1587/transinf.2020EDP7049
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2021
AB - This paper presents a pruning method, Reconstruction Error Aware Pruning (REAP), to reduce the redundancy of convolutional neural network models for accelerating their inference. In REAP, we have the following steps: 1) Prune the channels whose outputs are redundant and can be reconstructed from the outputs of other channels in each convolutional layer; 2) Update the weights of the remaining channels by least squares method so as to compensate the error caused by pruning. This is how we compress and accelerate the models that are initially large and slow with little degradation. The ability of REAP to maintain the model performances saves us lots of time and labors for retraining the pruned models. The challenge of REAP is the computational cost for selecting the channels to be pruned. For selecting the channels, we need to solve a huge number of least squares problems. We have developed an efficient algorithm based on biorthogonal system to obtain the solutions of those least squares problems. In the experiments, we show that REAP can conduct pruning with smaller sacrifice of the model performances than several existing methods including the previously state-of-the-art one.
ER -