2021/10/28 by Zhuangzhi Chen, Jingyang Xiang, Chen, Zhuangzhi +7
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2110.15192
13 pages, 9 figures, 3 tables
openalex publication_date 2021/10/28 · arxiv created 2021/11/18 · arxiv updated 2021/11/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Lightweight model design has become an important direction in the application of deep learning technology, pruning is an effective mean to achieve a large reduction in model parameters and FLOPs. The existing neural network pruning methods mostly start from the importance of parameters, and design parameter evaluation metrics to perform parameter pruning iteratively. These methods are not studied from the perspective of model topology, may be effective but not efficient, and requires completely different pruning for different datasets. In this paper, we study the graph structure of the neural network, and propose regular graph based pruning (RGP) to perform a one-shot neural network pruning. We generate a regular graph, set the node degree value of the graph to meet the pruning ratio, and reduce the average shortest path length of the graph by swapping the edges to obtain the optimal edge distribution. Finally, the obtained graph is mapped into a neural network structure to realize pruning. Experiments show that the average shortest path length of the graph is negatively correlated with the classification accuracy of the corresponding neural network, and the proposed RGP shows a strong precision retention capability with extremely high parameter reduction (more than 90%) and FLOPs reduction (more than 90%).