# On the role of population heterogeneity in emergent communication

arXiv: https://arxiv.org/abs/2204.12982 · HTML: https://mlsanity.com/paper/2204.12982/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2022.

## Built on by (most cited first, 24 of 24)

- [Emergent Communication: Generalization and Overfitting in Lewis Games](https://mlsanity.com/paper/2209.15342/) (2022)
- [Iterated Learning Improves Compositionality in Large Vision-Language Models](https://mlsanity.com/paper/2404.02145/) (2024)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure](https://mlsanity.com/paper/2302.12239/) (2023)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments](https://mlsanity.com/paper/2311.04453/) (2023)
- [Referential communication in heterogeneous communities of pre-trained visual deep networks](https://mlsanity.com/paper/2302.08913/) (2023)
- [Language Evolution with Deep Learning](https://mlsanity.com/paper/2403.11958/) (2024)
- [Over-communicate no more: Situated RL agents learn concise communication protocols](https://mlsanity.com/paper/2211.01480/) (2022)
- [Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments](https://mlsanity.com/paper/2209.10958/) (2022)
- [Mathematically Modeling the Lexicon Entropy of Emergent Language](https://mlsanity.com/paper/2211.15783/) (2022)
- [A framework for the emergence and analysis of language in social learning agents](https://mlsanity.com/paper/2305.02632/) (2023)
- [Emergent Communication with Attention](https://mlsanity.com/paper/2305.10920/) (2023)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)
- [Implicit Repair with Reinforcement Learning in Emergent Communication](https://mlsanity.com/paper/2502.12624/) (2025)
- [On the Correspondence between Compositionality and Imitation in Emergent Neural Communication](https://mlsanity.com/paper/2305.12941/) (2023)
- [PACE: Procedural Abstractions for Communicating Efficiently](https://mlsanity.com/paper/2409.20120/) (2024)
- [From Grunts to Lexicons: Emergent Language from Cooperative Foraging](https://mlsanity.com/paper/2505.12872/) (2025)
- [Emergent Compositional Communication for Latent World Properties](https://mlsanity.com/paper/2604.03266/) (2026)
- [Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells](https://mlsanity.com/paper/2609.11365/) (2026)
- [Emergent Communication for Rules Reasoning](https://mlsanity.com/paper/2311.04474/) (2023)
- [Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scale](https://mlsanity.com/paper/2401.08461/) (2024)
- [VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization](https://mlsanity.com/paper/2503.04940/) (2025)
- [Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning](https://mlsanity.com/paper/2605.11695/) (2026)

## Abstract (arXiv)

Populations have often been perceived as a structuring component for language to emerge and evolve: the larger the population, the more structured the language. While this observation is widespread in the sociolinguistic literature, it has not been consistently reproduced in computer simulations with neural agents. In this paper, we thus aim to clarify this apparent contradiction. We explore emergent language properties by varying agent population size in the speaker-listener Lewis Game. After reproducing the experimental difference, we challenge the simulation assumption that the agent community is homogeneous. We first investigate how speaker-listener asymmetry alters language structure to examine two potential diversity factors: training speed and network capacity. We find out that emergent language properties are only altered by the relative difference of learning speeds between speaker and listener, and not by their absolute values. From then, we leverage this observation to control population heterogeneity without introducing confounding factors. We finally show that introducing such training speed heterogeneities naturally sort out the initial contradiction: larger simulated communities start developing more stable and structured languages.