Kronecker CP Decomposition With Fast Multiplication for Compressing RNNs

Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, because the modern RNNs have complex topologies and expensive space/computation complexity, compressing them becomes a hot and promising topic i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2023-05, Vol.34 (5), p.2205-2219
Main Authors: Wang, Dingheng, Wu, Bijiao, Zhao, Guangshe, Yao, Man, Chen, Hengnu, Deng, Lei, Yan, Tianyi, Li, Guoqi
Format: Article
Language:English
Subjects:
Algorithms
Complexity
Compressing
Compression
Compression ratio
Computational complexity
Computational efficiency
Decomposition
Fast multiplication
Kronecker CP decomposition
Kronecker tensor (KT) decomposition
Mathematical analysis
Matrix decomposition
Natural language processing
network compression
Neural networks
Recurrent neural networks
recurrent neural networks (RNNs)
Sparse matrices
Task analysis
Tensors
Topology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, because the modern RNNs have complex topologies and expensive space/computation complexity, compressing them becomes a hot and promising topic in recent years. Among plenty of compression methods, tensor decomposition, e.g., tensor train (TT), block term (BT), tensor ring (TR), and hierarchical Tucker (HT), appears to be the most amazing approach because a very high compression ratio might be obtained. Nevertheless, none of these tensor decomposition formats can provide both space and computation efficiency. In this article, we consider to compress RNNs based on a novel Kronecker CANDECOMP/PARAFAC (KCP) decomposition, which is derived from Kronecker tensor (KT) decomposition, by proposing two fast algorithms of multiplication between the input and the tensor-decomposed weight. According to our experiments based on UCF11, Youtube Celebrities Face, UCF50, TIMIT, TED-LIUM, and Spiking Heidelberg digits datasets, it can be verified that the proposed KCP-RNNs have a comparable performance of accuracy with those in other tensor-decomposed formats, and even 278 219\times compression ratio could be obtained by the low-rank KCP. More importantly, KCP-RNNs are efficient in both space and computation complexity compared with other tensor-decomposed ones. Besides, we find KCP has the best potential of parallel computing to accelerate the calculations in neural networks.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2021.3105961