Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data

Recently, neural network compression schemes like channel pruning have been widely used to reduce the model size and computational complexity of deep neural networks (DNNs) for applications in power-constrained scenarios, such as embedded systems. Reinforcement learning (RL)-based auto-pruning has b...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on computer-aided design of integrated circuits and systems Vol. 43; no. 2; p. 1
Main Authors Mu, Jiandong, Wang, Mengdi, Zhu, Feiwen, Yang, Jun, Lin, Wei, Zhang, Wei
Format Journal Article
LanguageEnglish
Published New York IEEE 01.02.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial neural networks
Auto-pruning
Convergence
Data models
DNN
Embedded systems
Machine learning
Neural networks
Pruning
Reinforcement Learning
Search problems
Shears
Task analysis
Training
Transfer learning
Online AccessGet full text

Cover

More Information
Summary:Recently, neural network compression schemes like channel pruning have been widely used to reduce the model size and computational complexity of deep neural networks (DNNs) for applications in power-constrained scenarios, such as embedded systems. Reinforcement learning (RL)-based auto-pruning has been further proposed to automate the DNN pruning process to avoid expensive hand-crafted work. However, the RL-based pruner involves a time-consuming training process, and pruning and evaluating each network comes at high computational expense. These problems have greatly restricted the real-world application of RL-based auto-pruning. Thus, we propose an efficient auto-pruning framework that solves this problem by taking advantage of the historical data from the previous auto-pruning process. In our framework, we first boost the convergence of the RL-pruner by transfer learning. Then, an augmented transfer learning scheme is proposed to further speed up the training process by improving the transferability. Finally, an assistant learning process is proposed to improve the sample efficiency of the RL agent. The experiments show that our framework can accelerate the auto-pruning process by 1.5x 2.5x for ResNet20, and 1.81x 2.375x for other neural networks, such as ResNet56, ResNet18, and MobileNet v1.
ISSN:0278-0070
1937-4151
DOI:10.1109/TCAD.2023.3319594