# RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning

arXiv: https://arxiv.org/abs/2311.02123 · HTML: https://mlsanity.com/paper/2311.02123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 3 Nov 2023.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Stochastic Video Generation with a Learned Prior](https://mlsanity.com/paper/1802.07687/) (2018)
- [Stochastic Variational Video Prediction](https://mlsanity.com/paper/1710.11252/) (2017)
- [Recurrent Independent Mechanisms](https://mlsanity.com/paper/1909.10893/) (2019)
- [Sequence to Sequence -- Video to Text](https://mlsanity.com/paper/1505.00487/) (2015)
- [Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN](https://mlsanity.com/paper/1803.04831/) (2018)
- [Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning](https://mlsanity.com/paper/1711.01239/) (2017)
- [Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions](https://mlsanity.com/paper/1802.10353/) (2018)
- [A Clockwork RNN](https://mlsanity.com/paper/1402.3511/) (2014)
- [Relational recurrent neural networks](https://mlsanity.com/paper/1806.01822/) (2018)
- [Modular Networks: Learning to Decompose Neural Computation](https://mlsanity.com/paper/1811.05249/) (2018)
- [Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations](https://mlsanity.com/paper/1606.01305/) (2016)
- [Tracking the World State with Recurrent Entity Networks](https://mlsanity.com/paper/1612.03969/) (2016)
- [Wasserstein Learning of Deep Generative Point Process Models](https://mlsanity.com/paper/1705.08051/) (2017)
- [Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules](https://mlsanity.com/paper/2006.16981/) (2020)
- [Recurrent Highway Networks](https://mlsanity.com/paper/1607.03474/) (2016)
- [Fast and Slow Learning of Recurrent Independent Mechanisms](https://mlsanity.com/paper/2105.08710/) (2021)
- [Deep Attention Recurrent Q-Network](https://mlsanity.com/paper/1512.01693/) (2015)
- [Grid Long Short-Term Memory](https://mlsanity.com/paper/1507.01526/) (2015)
- [One Big Net For Everything](https://mlsanity.com/paper/1802.08864/) (2018)

## Abstract (arXiv)

Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms. Learning such a modular structure can often improve the robustness against environmental changes. In this paper, we propose recurrent independent Grid LSTM (RigLSTM), composed of a group of independent LSTM cells that cooperate with each other, for exploiting the underlying modular structure of the target task. Our model adopts cell selection, input feature selection, hidden state selection, and soft state updating to achieve a better generalization ability on the basis of the recent Grid LSTM for the tasks where some factors differ between training and evaluation. Specifically, at each time step, only a fraction of cells are activated, and the activated cells select relevant inputs and cells to communicate with. At the end of one time step, the hidden states of the activated cells are updated by considering the relevance between the inputs and the hidden states from the last and current time steps. Extensive experiments on diversified sequential modeling tasks are conducted to show the superior generalization ability when there exist changes in the testing environment. Source code is available at urlhttps://github.com/ziyuwwang/rig-lstm.