Restricted Recurrent Neural Networks

Enmao DIao, Jie DIng, Vahid Tarokh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Recurrent Neural Network (RNN) and its variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), have become standard building blocks for learning online data of sequential nature in many research areas, including natural language processing and speech data analysis. In this paper, we present a new methodology to significantly reduce the number of parameters in RNNs while maintaining performance that is comparable or even better than classical RNNs. The new proposal, referred to as Restricted Recurrent Neural Network (RRNN), restricts the weight matrices corresponding to the input data and hidden states at each time step to share a large proportion of parameters. The new architecture can be regarded as a compression of its classical counterpart, but it does not require pre-training or sophisticated parameter fine-tuning, both of which are major issues in most existing compression techniques. Experiments on natural language modeling show that compared with its classical counterpart, the restricted recurrent architecture generally produces comparable results at about 50% compression rate. In particular, the Restricted LSTM can outperform classical RNN with even less number of parameters.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE International Conference on Big Data, Big Data 2019
EditorsChaitanya Baru, Jun Huan, Latifur Khan, Xiaohua Tony Hu, Ronay Ak, Yuanyuan Tian, Roger Barga, Carlo Zaniolo, Kisung Lee, Yanfang Fanny Ye
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages56-63
Number of pages8
ISBN (Electronic)9781728108582
DOIs
StatePublished - Dec 2019
Event2019 IEEE International Conference on Big Data, Big Data 2019 - Los Angeles, United States
Duration: Dec 9 2019Dec 12 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Big Data, Big Data 2019

Conference

Conference2019 IEEE International Conference on Big Data, Big Data 2019
CountryUnited States
CityLos Angeles
Period12/9/1912/12/19

Bibliographical note

Funding Information:
This work was supported in part by Office of Naval Research Grant No. N00014-18-1-2244. We provide our implementation at https://github.com/ dem123456789/Restricted-Recurrent-Neural-Networks. 978-1-7281-0858-2/19/$31.00 © 2019 IEEE

Keywords

  • Gated Recurrent Unit
  • Long Short-Term Memory
  • Model Compression
  • Parameter Sharing
  • Recurrent Neural Networks

Fingerprint Dive into the research topics of 'Restricted Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this