A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions

TL;DR

This paper provides a comprehensive survey of deep neural network compression techniques, categorizing methods like pruning, sparse representation, quantization, and knowledge distillation, highlighting challenges and future directions for resource-constrained IoT applications.

Contribution

It offers a detailed overview and classification of existing DNN compression methods, along with analysis of challenges and future research directions.

Findings

Five main categories of DNN compression techniques identified.

Challenges vary across different compression methods.

Future research directions outlined for each category.

Abstract

Deep Neural Network (DNN) has gained unprecedented performance due to its automated feature extraction capability. This high order performance leads to significant incorporation of DNN models in different Internet of Things (IoT) applications in the past decade. However, the colossal requirement of computation, energy, and storage of DNN models make their deployment prohibitive on resource constraint IoT devices. Therefore, several compression techniques were proposed in recent years for reducing the storage and computation requirements of the DNN model. These techniques on DNN compression have utilized a different perspective for compressing DNN with minimal accuracy compromise. It encourages us to make a comprehensive overview of the DNN compression techniques. In this paper, we present a comprehensive review of existing literature on compressing DNN model that reduces both storage and computation requirements. We divide the existing approaches into five broad categories, i.e., network pruning, sparse representation, bits precision, knowledge distillation, and miscellaneous, based upon the mechanism incorporated for compressing the DNN model. The paper also discussed the challenges associated with each category of DNN compression techniques. Finally, we provide a quick summary of existing work under each category with the future direction in DNN compression.