中文版 | English
Title

Robust Neural Network Pruning by Cooperative Coevolution

Author
Corresponding AuthorQian,Chao
DOI
Publication Years
2022
Conference Name
17th International Conference on Parallel Problem Solving from Nature (PPSN)
ISSN
0302-9743
EISSN
1611-3349
ISBN
978-3-031-14713-5
Source Title
Volume
13398 LNCS
Pages
459-473
Conference Date
SEP 10-14, 2022
Conference Place
null,Dortmund,GERMANY
Publication Place
GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
Publisher
Abstract
Convolutional neural networks have achieved success in various tasks, but often lack compactness and robustness, which are, however, required under resource-constrained and safety-critical environments. Previous works mainly focused on enhancing either compactness or robustness of neural networks, such as network pruning and adversarial training. Robust neural network pruning aims to reduce computational cost while preserving both accuracy and robustness of a network. Existing robust pruning works usually require expert experiences and trial-and-error to design proper pruning criteria or auxiliary modules, limiting their applications. Meanwhile, evolutionary algorithms (EAs) have been used to prune neural networks automatically, achieving impressive results but without considering the robustness. In this paper, we propose a novel robust pruning method CCRP by cooperative coevolution. Specifically, robust pruning is formulated as a three-objective optimization problem that optimizes accuracy, robustness and compactness simultaneously, and solved by a cooperative coevolution pruning framework, which prunes filters in each layer by EAs separately. The experiments on CIFAR-10 and SVHN show that CCRP can achieve comparable performance with state-of-the-art methods.
Keywords
SUSTech Authorship
Others
Language
English
URL[Source Record]
Indexed By
Funding Project
NSFC["62022039","62106098"] ; Jiangsu NSF[BK20201247]
WOS Research Area
Computer Science
WOS Subject
Computer Science, Artificial Intelligence
WOS Accession No
WOS:000871752100032
EI Accession Number
20223512669288
EI Keywords
Safety engineering
ESI Classification Code
Safety Engineering:914
Scopus EID
2-s2.0-85136948397
Data Source
Scopus
Citation statistics
Cited Times [WOS]:0
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/401669
DepartmentDepartment of Computer Science and Engineering
Affiliation
1.State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing,210023,China
2.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
Recommended Citation
GB/T 7714
Wu,Jia Liang,Shang,Haopu,Hong,Wenjing,et al. Robust Neural Network Pruning by Cooperative Coevolution[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:459-473.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Wu,Jia Liang]'s Articles
[Shang,Haopu]'s Articles
[Hong,Wenjing]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Wu,Jia Liang]'s Articles
[Shang,Haopu]'s Articles
[Hong,Wenjing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wu,Jia Liang]'s Articles
[Shang,Haopu]'s Articles
[Hong,Wenjing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.