Learning and Compressing: Low-Rank Matrix Factorization for Deep Neural Network Compression

Abstract

Recently, the deep neural network (DNN) has become one of the most advanced and powerful methods used in classification tasks. However, the cost of DNN models is sometimes considerable due to the huge sets of parameters. Therefore, it is necessary to compress these models in order to reduce the parameters in weight matrices and decrease computational consumption, while maintaining the same level of accuracy. In this paper, in order to deal with the compression problem, we first combine the loss function and the compression cost function into a joint function, and optimize it as an optimization framework. Then we combine the CUR decomposition method with this joint optimization framework to obtain the low-rank approximation matrices. Finally, we narrow the gap between the weight matrices and the low-rank approximations to compress the DNN models on the image classification task. In this algorithm, we not only solve the optimal ranks by enumeration, but also obtain the compression result with low-rank characteristics iteratively. Experiments were carried out on three public datasets under classification tasks. Comparisons with baselines and current state-of-the-art results can conclude that our proposed low-rank joint optimization compression algorithm can achieve higher accuracy and compression ratios.