# Selfish Sparse RNN Training

arXiv: https://arxiv.org/abs/2101.09048 · HTML: https://mlsanity.com/paper/2101.09048/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 77 references that are in the map.
- First posted on arXiv 22 Jan 2021.

## Builds on (most cited first, 30 of 53)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [Essentially No Barriers in Neural Network Energy Landscape](https://mlsanity.com/paper/1803.00885/) (2018)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [Speeding up Convolutional Neural Networks with Low Rank Expansions](https://mlsanity.com/paper/1405.3866/) (2014)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [Convergent Learning: Do different neural networks learn the same representations?](https://mlsanity.com/paper/1511.07543/) (2015)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [Sparse Networks from Scratch: Faster Training without Losing Performance](https://mlsanity.com/paper/1907.04840/) (2019)
- [Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask](https://mlsanity.com/paper/1905.01067/) (2019)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [Recurrent Neural Network Regularization](https://mlsanity.com/paper/1409.2329/) (2014)
- [Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization](https://mlsanity.com/paper/1902.05967/) (2019)
- [Qualitatively characterizing neural network optimization problems](https://mlsanity.com/paper/1412.6544/) (2014)
- [Training Very Deep Networks](https://mlsanity.com/paper/1507.06228/) (2015)
- [A Theoretically Grounded Application of Dropout in Recurrent Neural Networks](https://mlsanity.com/paper/1512.05287/) (2015)

## Built on by (most cited first, 26 of 26)

- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training](https://mlsanity.com/paper/2102.02887/) (2021)
- [Sparse Training via Boosting Pruning Plasticity with Neuroregeneration](https://mlsanity.com/paper/2106.10404/) (2021)
- [Dynamic Sparse Training for Deep Reinforcement Learning](https://mlsanity.com/paper/2106.04217/) (2021)
- [Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity](https://mlsanity.com/paper/2106.14568/) (2021)
- [Sparsity Winning Twice: Better Robust Generalization from More Efficient Training](https://mlsanity.com/paper/2202.09844/) (2022)
- [NTK-SAP: Improving neural network pruning by aligning training dynamics](https://mlsanity.com/paper/2304.02840/) (2023)
- [The Elastic Lottery Ticket Hypothesis](https://mlsanity.com/paper/2103.16547/) (2021)
- [Dynamic Sparse Network for Time Series Classification: Learning What to "see''](https://mlsanity.com/paper/2212.09840/) (2022)
- [EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization](https://mlsanity.com/paper/2307.10554/) (2023)
- [Truly Sparse Neural Networks at Scale](https://mlsanity.com/paper/2102.01732/) (2021)
- [Where to Pay Attention in Sparse Training for Feature Selection?](https://mlsanity.com/paper/2211.14627/) (2022)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)
- [Sparse Training Theory for Scalable and Efficient Agents](https://mlsanity.com/paper/2103.01636/) (2021)
- [Towards Structured Dynamic Sparse Pre-Training of BERT](https://mlsanity.com/paper/2108.06277/) (2021)
- [Balanced Training for Sparse GANs](https://mlsanity.com/paper/2302.14670/) (2023)
- [Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency](https://mlsanity.com/paper/2303.11525/) (2023)
- [Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction](https://mlsanity.com/paper/2406.04934/) (2024)
- [Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance](https://mlsanity.com/paper/2203.02770/) (2022)
- [Training Large Language Models Efficiently with Sparsity and Dataflow](https://mlsanity.com/paper/2304.05511/) (2023)
- [Spectral Pruning for Recurrent Neural Networks](https://mlsanity.com/paper/2105.10832/) (2021)
- [Experiments on Properties of Hidden Structures of Sparse Neural Networks](https://mlsanity.com/paper/2107.12917/) (2021)
- [Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers](https://mlsanity.com/paper/2305.18382/) (2023)
- [Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum](https://mlsanity.com/paper/2506.07975/) (2025)
- [Transformer-Encoder-GRU (T-E-GRU) for Chinese Sentiment Analysis on Chinese Comment Text](https://mlsanity.com/paper/2108.00400/) (2021)
- [Language Modeling With Factorization Memory](https://mlsanity.com/paper/2511.00315/) (2025)

## Abstract (arXiv)

Sparse neural networks have been widely applied to reduce the computational demands of training and deploying over-parameterized deep neural networks. For inference acceleration, methods that discover a sparse network from a pre-trained dense network (dense-to-sparse training) work effectively. Recently, dynamic sparse training (DST) has been proposed to train sparse neural networks without pre-training a dense model (sparse-to-sparse training), so that the training process can also be accelerated. However, previous sparse-to-sparse methods mainly focus on Multilayer Perceptron Networks (MLPs) and Convolutional Neural Networks (CNNs), failing to match the performance of dense-to-sparse methods in the Recurrent Neural Networks (RNNs) setting. In this paper, we propose an approach to train intrinsically sparse RNNs with a fixed parameter count in one single run, without compromising performance. During training, we allow RNN layers to have a non-uniform redistribution across cell gates for better regularization. Further, we propose SNT-ASGD, a novel variant of the averaged stochastic gradient optimizer, which significantly improves the performance of all sparse training methods for RNNs. Using these strategies, we achieve state-of-the-art sparse training results, better than the dense-to-sparse methods, with various types of RNNs on Penn TreeBank and Wikitext-2 datasets. Our codes are available at https://github.com/Shiweiliuiiiiiii/Selfish-RNN.