Year: 2024
Type: article
Abstract: Neural network pruning, the process of removing unnecessary weights or neurons from a neural network model, has become an essential technique for reducing computational cost and increasing processing speed, thereby improving overall performance. This article has grouped current pruning methods into three classes—channel pruning, filter pruning, and parameter sparsification—and discussed how each method works. Each approach has its own strengths: channel pruning is particularly useful for reducing model depth and width, filter pruning is more suitable for maintaining model depth while decreasing storage requirements, and parameter sparsification can be applied across various network architectures to achieve both storage and computational efficiency. This work will delve into how each method works and highlight key related works of each category. In the future, it is expected that future research in neural network pruning could focus on developing more sophisticated techniques that can automatically identify important weights or neurons within a network.
Authors: Longxiang Gou, Ziyi Han, Zhimeng Yuan
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4393230987
