Computer and Modernization ›› 2022, Vol. 0 ›› Issue (09): 51-59.

Previous Articles     Next Articles

Survey of Model Pruning Algorithms

  

  1. (1. Cashway Fintech Co. Ltd., Tianjin 300308, China;
    2. College of Intelligence and Computing, Tianjin University, Tianjin 300350, China)
  • Online:2022-09-22 Published:2022-09-22

Abstract: The model pruning algorithms apply different standards or methods to prune the redundant neurons in the deep neural network, which can compress the model to the maximum extent without losing the accuracy of the model, so as to reduce the storage and improve the speed. Firstly, the research status of model pruning algorithm and the main research direction are summarized and classified. The main research areas of model pruning include the granularity of pruning, the method to evaluate the importance of pruning elements, the sparsity of pruning, the theoretical foundation of model pruning, pruning for different tasks and so on. Then, the recent representative pruning algorithms are described in detail as well. Finally, the future research direction in this field is brought forward.

Key words: model pruning, deep learning, channel, threshold, compression