Kronecker CP Decomposition With Fast Multiplication for Compressing RNNs

Dingheng Wang, Bijiao Wu, Guangshe Zhao, Man Yao, Hengnu Chen, Lei Deng, Tianyi Yan*, Guoqi Li*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)

Abstract

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× 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.

Original languageEnglish
Pages (from-to)2205-2219
Number of pages15
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume34
Issue number5
DOIs
Publication statusPublished - 1 May 2023

Keywords

  • Fast multiplication
  • Kronecker CP decomposition
  • Kronecker tensor (KT) decomposition
  • network compression
  • recurrent neural networks (RNNs)

Fingerprint

Dive into the research topics of 'Kronecker CP Decomposition With Fast Multiplication for Compressing RNNs'. Together they form a unique fingerprint.

Cite this