A framework for automatic identification of neural network structural redundancy based on reinforcement learning

Tingting Wu; Chunhe Song; Peng Zeng

doi:10.1117/12.2668217

28 March 2023 A framework for automatic identification of neural network structural redundancy based on reinforcement learning

Tingting Wu, Chunhe Song, Peng Zeng

Author Affiliations +

Proceedings Volume 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022); 1256630 (2023) https://doi.org/10.1117/12.2668217
Event: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 2022, Chongqing, China

Abstract

The increasing structure of neural networks makes it difficult to deploy on edge devices with limited computing resources. Network pruning has become one of the most successful model compression methods in recent years. Existing works usually compress models by removing unimportant filters based on the importance. However, the importance-based algorithms tend to ignore the parameters that extract edge features with small criterion values. And recent studies have shown that the existing criteria rely on norm and lead to similar model compression structures. Aiming at the problems of ignoring edge features and manually specifying the pruning rate in current importance-based model pruning algorithms, this paper proposes an automatic recognition framework for neural network structure redundancy based on reinforcement learning. First, we perform cluster analysis on the filters of each layer, and map the filters into a multi-dimensional space to generate similar sets with different functions. We then propose a criterion for identifying redundant filters within similar sets. Finally, we use reinforcement learning to automatically optimize the cluster dimension, and then determine the optimal pruning rate for each layer to reduce the performance loss caused by pruning. Extensive experiments on various benchmark network architectures and datasets demonstrate the effectiveness of our proposed framework.

Citation Download Citation

Tingting Wu, Chunhe Song, and Peng Zeng "A framework for automatic identification of neural network structural redundancy based on reinforcement learning", Proc. SPIE 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 1256630 (28 March 2023); https://doi.org/10.1117/12.2668217

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available