# The Emergence of the Shape Bias Results from Communicative Efficiency

arXiv: https://arxiv.org/abs/2109.06232 · HTML: https://mlsanity.com/paper/2109.06232/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 62 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [Are Convolutional Neural Networks or Transformers more like human vision?](https://mlsanity.com/paper/2105.07197/) (2021)
- [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)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [Ease-of-Teaching and Language Structure from Emergent Communication](https://mlsanity.com/paper/1906.02403/) (2019)
- [Emergent Communication through Negotiation](https://mlsanity.com/paper/1804.03980/) (2018)
- [Countering Language Drift with Seeded Iterated Learning](https://mlsanity.com/paper/2003.12694/) (2020)
- [Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study](https://mlsanity.com/paper/1706.08606/) (2017)
- [How agents see things: On visual representations in an emergent language game](https://mlsanity.com/paper/1808.10696/) (2018)
- [Emergent Linguistic Phenomena in Multi-Agent Communication Games](https://mlsanity.com/paper/1901.08706/) (2019)
- [Assessing Shape Bias Property of Convolutional Neural Networks](https://mlsanity.com/paper/1803.07739/) (2018)
- [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)
- [Color naming reflects both perceptual structure and communicative need](https://mlsanity.com/paper/1805.06165/) (2018)
- [Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances](https://mlsanity.com/paper/1905.11871/) (2019)

## Built on by (most cited first, 13 of 13)

- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification](https://mlsanity.com/paper/2210.12843/) (2022)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Emergent Language: A Survey and Taxonomy](https://mlsanity.com/paper/2409.02645/) (2024)
- [A systematic framework for generating novel experimental hypotheses from language models](https://mlsanity.com/paper/2408.05086/) (2024)
- [Adopting a human developmental visual diet yields robust, shape-based AI vision](https://mlsanity.com/paper/2507.03168/) (2025)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)
- [Contrastive Multimodal Learning for Emergence of Graphical Sensory-Motor Communication](https://mlsanity.com/paper/2210.06468/) (2022)
- [A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations](https://mlsanity.com/paper/2212.06021/) (2022)
- [Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods](https://mlsanity.com/paper/2206.01251/) (2022)
- [Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scale](https://mlsanity.com/paper/2401.08461/) (2024)
- [Would you still call this Dax? Novel Visual References in VLMs and Humans](https://mlsanity.com/paper/2606.05409/) (2026)
- [Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations](https://mlsanity.com/paper/2609.06025/) (2026)

## Abstract (arXiv)

By the age of two, children tend to assume that new word categories are based on objects' shape, rather than their color or texture; this assumption is called the shape bias. They are thought to learn this bias by observing that their caregiver's language is biased towards shape based categories. This presents a chicken and egg problem: if the shape bias must be present in the language in order for children to learn it, how did it arise in language in the first place? In this paper, we propose that communicative efficiency explains both how the shape bias emerged and why it persists across generations. We model this process with neural emergent language agents that learn to communicate about raw pixelated images. First, we show that the shape bias emerges as a result of efficient communication strategies employed by agents. Second, we show that pressure brought on by communicative need is also necessary for it to persist across generations; simply having a shape bias in an agent's input language is insufficient. These results suggest that, over and above the operation of other learning strategies, the shape bias in human learners may emerge and be sustained by communicative pressures.