Robust Neural Network Pruning by Cooperative Coevolution

Wu，Jia Liang1; Shang，Haopu1; Hong，Wenjing2; Qian，Chao1

10.1007/978-3-031-14714-2_32

2022

17th International Conference on Parallel Problem Solving from Nature (PPSN)

0302-9743

1611-3349

978-3-031-14713-5

LECT NOTES ARTIF INT

13398 LNCS

459-473

SEP 10-14, 2022

null,Dortmund,GERMANY

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

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.

Cooperative coevolution Evolutionary algorithm Model compression Neural network pruning Robustness

其他

英语

EI ; CPCI-S

NSFC["62022039","62106098"] ; Jiangsu NSF[BK20201247]

Computer Science

Computer Science, Artificial Intelligence

WOS:000871752100032

20223512669288

Safety engineering

Safety Engineering:914

2-s2.0-85136948397

Scopus

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

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.