# Compositional Generalization in Grounded Language Learning via Induced Model Sparsity

arXiv: https://arxiv.org/abs/2207.02518 · HTML: https://mlsanity.com/paper/2207.02518/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 6 Jul 2022.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning](https://mlsanity.com/paper/1810.08272/) (2018)
- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [Value Iteration Networks](https://mlsanity.com/paper/1602.02867/) (2016)
- [When to use parametric models in reinforcement learning?](https://mlsanity.com/paper/1906.05243/) (2019)
- [A Benchmark for Systematic Generalization in Grounded Language Understanding](https://mlsanity.com/paper/2003.05161/) (2020)
- [Grounded Language Learning in a Simulated 3D World](https://mlsanity.com/paper/1706.06551/) (2017)
- [Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning](https://mlsanity.com/paper/1706.05064/) (2017)
- [Leveraging Sparse Linear Layers for Debuggable Deep Networks](https://mlsanity.com/paper/2105.04857/) (2021)
- [Learning to Understand Goal Specifications by Modelling Reward](https://mlsanity.com/paper/1806.01946/) (2018)
- [Top-KAST: Top-K Always Sparse Training](https://mlsanity.com/paper/2106.03517/) (2021)
- [DeepMind Lab](https://mlsanity.com/paper/1612.03801/) (2016)
- [Gated-Attention Architectures for Task-Oriented Language Grounding](https://mlsanity.com/paper/1706.07230/) (2017)
- [Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2101.07393/) (2021)
- [A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2106.02097/) (2021)
- [Working Memory Graphs](https://mlsanity.com/paper/1911.07141/) (2019)
- [Compositional Networks Enable Systematic Generalization for Grounded Language Understanding](https://mlsanity.com/paper/2008.02742/) (2020)
- [Systematic Generalization on gSCAN with Language Conditioned Embedding](https://mlsanity.com/paper/2009.05552/) (2020)
- [Zero-shot Task Adaptation using Natural Language](https://mlsanity.com/paper/2106.02972/) (2021)

## Built on by (most cited first, 4 of 4)

- [Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task](https://mlsanity.com/paper/2310.09336/) (2023)
- [Swing-by Dynamics in Concept Learning and Compositional Generalization](https://mlsanity.com/paper/2410.08309/) (2024)
- [Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning](https://mlsanity.com/paper/2501.15270/) (2025)
- [Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds](https://mlsanity.com/paper/2606.19941/) (2026)

## Abstract (arXiv)

We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems. We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We show that standard neural architectures do not always yield compositional generalization. To address this, we design an agent that contains a goal identification module that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. The output of the goal identification module is the input to a value iteration network planner. Our agent maintains a high level of performance on goals containing novel combinations of properties even when learning from a handful of demonstrations. We examine the internal representations of our agent and find the correct correspondences between words in its dictionary and attributes in the environment.