Shaowu Chen

Shaowu Chen

Auto-generated profile, based on publicly available information

Shaowu Chen

Shenzhen Polytechnic University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 November 2020 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
WSWeize Sun
Weize Sun
SCShaowu Chen
Shaowu Chen
LHLei Huang
Lei Huang
HSHing Cheung So
Hing Cheung So
MXMin Xie
Min Xie
Large neural networks have aroused impressive progress in various real world applications. However, the expensive storage and computational resources requirement for running deep networks make them problematic to be deployed on mobile devices. Recently, matrix and tensor decompositions have been employed for compressing neural networks. In this paper, we develop a simultaneous tensor decomposition technique for network optimization. The shared network structure is first discussed. Sometimes, not only the structure but also the parameters are shared to form a compressed model at the expense of degraded performance. This indicates that the weight tensors between layers within one network contain both identical components and independent components. To utilize this characteristic, two new coupled tensor train decompositions are developed for fully and partly structure sharing cases, and an alternating optimization approach is proposed for low rank tensor computation. Finally, we restore the performance of the neural network model by fine-tuning. The compression ratio of the devised approach can then be calculated. Experimental results are also included to demonstrate the benefits of our algorithm for both applications of image reconstruction and classification, using the well known datasets such as Cifar-10/Cifar-100 and ImageNet and widely used networks such as ResNet. Comparing to the state-of-the-art independent matrix and tensor decomposition based methods, our model can obtain a better network performance under the same compression ratio.

17 July 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
SCShaowu Chen
Shaowu Chen
WSWeize Sun
Weize Sun
LHLei Huang
Lei Huang
XLXiao Peng Li
Xiao Peng Li
QWQingyuan Wang
Qingyuan Wang
DJDeepu John
Deepu John

22 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
XLXuhua Li
Xuhua Li
WSWeize Sun
Weize Sun
LHLei Huang
Lei Huang
SCShaowu Chen
Shaowu Chen
Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs).Some research regarded filter pruning as a combinatorial optimization problem and thus used evolutionary algorithms (EA) to prune filters of DNNs. However, it is difficult to find a satisfactory compromise solution in a reasonable time due to the complexity of solution space searching. To solve this problem, we first formulate a multi-objective optimization problem based on a sub-network of the full model and propose a Sub-network Multiobjective Evolutionary Algorithm (SMOEA) for filter pruning. By progressively pruning the convolutional layers in groups, SMOEA can obtain a lightweight pruned result with better performance.Experiments on VGG-14 model for CIFAR-10 verify the effectiveness of the proposed SMOEA. Specifically, the accuracy of the pruned model with 16.56% parameters decreases by 0.28% only, which is better than the widely used popular filter pruning criteria.

1 January 2026 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
JQJundong Qi
Jundong Qi
WSWeize Sun
Weize Sun
SCShaowu Chen
Shaowu Chen
LHLei Huang
Lei Huang
QLQiuchen Liu
Qiuchen Liu

1 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
SCShaowu Chen
Shaowu Chen
WMWei Ma
Wei Ma
BHBinhua Huang
Binhua Huang
QWQingyuan Wang
Qingyuan Wang
GWGuoxin Wang
Guoxin Wang
DJDeepu John
Deepu John