# Iterated learning for emergent systematicity in VQA

arXiv: https://arxiv.org/abs/2105.01119 · HTML: https://mlsanity.com/paper/2105.01119/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 3 May 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Compositional Attention Networks for Machine Reasoning](https://mlsanity.com/paper/1803.03067/) (2018)
- [Inferring and Executing Programs for Visual Reasoning](https://mlsanity.com/paper/1705.03633/) (2017)
- [Learning to Reason: End-to-End Module Networks for Visual Question Answering](https://mlsanity.com/paper/1704.05526/) (2017)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [Compositionality and Generalization in Emergent Languages](https://mlsanity.com/paper/2004.09124/) (2020)
- [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018)
- [Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog](https://mlsanity.com/paper/1706.08502/) (2017)
- [Compositional Languages Emerge in a Neural Iterated Learning Model](https://mlsanity.com/paper/2002.01365/) (2020)
- [Ease-of-Teaching and Language Structure from Emergent Communication](https://mlsanity.com/paper/1906.02403/) (2019)
- [CLOSURE: Assessing Systematic Generalization of CLEVR Models](https://mlsanity.com/paper/1912.05783/) (2019)
- [Countering Language Drift with Seeded Iterated Learning](https://mlsanity.com/paper/2003.12694/) (2020)
- [Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering](https://mlsanity.com/paper/1902.07864/) (2019)
- [The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents](https://mlsanity.com/paper/1910.05291/) (2019)
- [Co-evolution of language and agents in referential games](https://mlsanity.com/paper/2001.03361/) (2020)
- [Emergence of Compositional Language with Deep Generational Transmission](https://mlsanity.com/paper/1904.09067/) (2019)
- [Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence](https://mlsanity.com/paper/1611.03218/) (2016)

## Built on by (most cited first, 21 of 21)

- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate](https://mlsanity.com/paper/2402.02769/) (2024)
- [Break It Down: Evidence for Structural Compositionality in Neural Networks](https://mlsanity.com/paper/2301.10884/) (2023)
- [Fortuitous Forgetting in Connectionist Networks](https://mlsanity.com/paper/2202.00155/) (2022)
- [Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics](https://mlsanity.com/paper/2109.13986/) (2021)
- [Multi-label Iterated Learning for Image Classification with Label Ambiguity](https://mlsanity.com/paper/2111.12172/) (2021)
- [Eliciting the Priors of Large Language Models using Iterated In-Context Learning](https://mlsanity.com/paper/2406.01860/) (2024)
- [Iterated Learning Improves Compositionality in Large Vision-Language Models](https://mlsanity.com/paper/2404.02145/) (2024)
- [Bias Amplification in Language Model Evolution: An Iterated Learning Perspective](https://mlsanity.com/paper/2404.04286/) (2024)
- [Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings](https://mlsanity.com/paper/2310.18777/) (2023)
- [On The Specialization of Neural Modules](https://mlsanity.com/paper/2409.14981/) (2024)
- [Concept-Best-Matching: Evaluating Compositionality in Emergent Communication](https://mlsanity.com/paper/2403.14705/) (2024)
- [lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning](https://mlsanity.com/paper/2401.08808/) (2024)
- [Attribute Diversity Determines the Systematicity Gap in VQA](https://mlsanity.com/paper/2311.08695/) (2023)
- [Unsupervised Translation of Emergent Communication](https://mlsanity.com/paper/2502.07552/) (2025)
- ["Forgetting" in Machine Learning and Beyond: A Survey](https://mlsanity.com/paper/2405.20620/) (2024)
- [Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks](https://mlsanity.com/paper/2503.06181/) (2025)
- [Sequential Compositional Generalization in Multimodal Models](https://mlsanity.com/paper/2404.12013/) (2024)
- [CtD: Composition through Decomposition in Emergent Communication](https://mlsanity.com/paper/2601.10169/) (2026)
- [Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods](https://mlsanity.com/paper/2206.01251/) (2022)

## Abstract (arXiv)

Although neural module networks have an architectural bias towards compositionality, they require gold standard layouts to generalize systematically in practice. When instead learning layouts and modules jointly, compositionality does not arise automatically and an explicit pressure is necessary for the emergence of layouts exhibiting the right structure. We propose to address this problem using iterated learning, a cognitive science theory of the emergence of compositional languages in nature that has primarily been applied to simple referential games in machine learning. Considering the layouts of module networks as samples from an emergent language, we use iterated learning to encourage the development of structure within this language. We show that the resulting layouts support systematic generalization in neural agents solving the more complex task of visual question-answering. Our regularized iterated learning method can outperform baselines without iterated learning on SHAPES-SyGeT (SHAPES Systematic Generalization Test), a new split of the SHAPES dataset we introduce to evaluate systematic generalization, and on CLOSURE, an extension of CLEVR also designed to test systematic generalization. We demonstrate superior performance in recovering ground-truth compositional program structure with limited supervision on both SHAPES-SyGeT and CLEVR.