# Restricted Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1908.07724 · HTML: https://mlsanity.com/paper/1908.07724/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2019.

## Built on by (most cited first, 5 of 5)

- [Pruning Deep Neural Networks from a Sparsity Perspective](https://mlsanity.com/paper/2302.05601/) (2023)
- [Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing](https://mlsanity.com/paper/2502.15618/) (2025)
- [Demystifying Poisoning Backdoor Attacks from a Statistical Perspective](https://mlsanity.com/paper/2310.10780/) (2023)
- [Emulating Spatio-Temporal Realizations of Three-Dimensional Isotropic Turbulence via Deep Sequence Learning Models](https://mlsanity.com/paper/2112.03469/) (2021)
- [DynamicFL: Federated Learning with Dynamic Communication Resource Allocation](https://mlsanity.com/paper/2409.04986/) (2024)

## Abstract (arXiv)

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.