English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Model compression plays a vital role in the practical deployment of deepneural networks (DNNs), and evolutionary multi-objective (EMO) pruning is anessential tool in balancing the compression rate and performance of the DNNs.However, due to its population-based nature, EMO pruning suffers from thecomplex optimization space and the resource-intensive structure verificationprocess, especially in complex networks. To this end, a multi-objective complexnetwork pruning framework based on divide-and-conquer and global performanceimpairment ranking (EMO-DIR) is proposed in this paper. Firstly, adivide-and-conquer EMO network pruning method is proposed, which decomposes thecomplex task of EMO pruning on the entire network into easier sub-tasks onmultiple sub-networks. On the one hand, this decomposition narrows the pruningoptimization space and decreases the optimization difficulty; on the otherhand, the smaller network structure converges faster, so the proposed algorithmconsumes lower computational resources. Secondly, a sub-network training methodbased on cross-network constraints is designed, which could bridge independentEMO pruning sub-tasks, allowing them to collaborate better and improving theoverall performance of the pruned network. Finally, a multiple sub-networksjoint pruning method based on EMO is proposed. This method combines the ParetoFronts from EMO pruning results on multiple sub-networks through globalperformance impairment ranking to design a joint pruning scheme. The richexperiments on CIFAR-10/100 and ImageNet-100/1k are conducted. The proposedalgorithm achieves a comparable performance with the state-of-the-art pruningmethods.

A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking