LGAIMar 28, 2023

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

arXiv:2303.16212v2h-index: 47
Originality Incremental advance
AI Analysis

This work addresses model compression for deploying deep neural networks, offering an incremental improvement in pruning efficiency.

The paper tackles the challenge of evolutionary multi-objective pruning for deep neural networks, which suffers from complex optimization and high computational costs, by proposing a divide-and-conquer framework that decomposes the network into sub-networks, achieving comparable performance to state-of-the-art methods on datasets like CIFAR-10/100 and ImageNet-100/1k.

Model compression plays a vital role in the practical deployment of deep neural networks (DNNs), and evolutionary multi-objective (EMO) pruning is an essential tool in balancing the compression rate and performance of the DNNs. However, due to its population-based nature, EMO pruning suffers from the complex optimization space and the resource-intensive structure verification process, especially in complex networks. To this end, a multi-objective complex network pruning framework based on divide-and-conquer and global performance impairment ranking (EMO-DIR) is proposed in this paper. Firstly, a divide-and-conquer EMO network pruning method is proposed, which decomposes the complex task of EMO pruning on the entire network into easier sub-tasks on multiple sub-networks. On the one hand, this decomposition narrows the pruning optimization space and decreases the optimization difficulty; on the other hand, the smaller network structure converges faster, so the proposed algorithm consumes lower computational resources. Secondly, a sub-network training method based on cross-network constraints is designed, which could bridge independent EMO pruning sub-tasks, allowing them to collaborate better and improving the overall performance of the pruned network. Finally, a multiple sub-networks joint pruning method based on EMO is proposed. This method combines the Pareto Fronts from EMO pruning results on multiple sub-networks through global performance impairment ranking to design a joint pruning scheme. The rich experiments on CIFAR-10/100 and ImageNet-100/1k are conducted. The proposed algorithm achieves a comparable performance with the state-of-the-art pruning methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes