# Shaping representations through communication: community size effect in artificial learning systems

arXiv: https://arxiv.org/abs/1912.06208 · HTML: https://mlsanity.com/paper/1912.06208/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2019.

## Built on by (most cited first, 14 of 14)

- [Few-shot Language Coordination by Modeling Theory of Mind](https://mlsanity.com/paper/2107.05697/) (2021)
- [From partners to populations: A hierarchical Bayesian account of coordination and convention](https://mlsanity.com/paper/2104.05857/) (2021)
- [Emergent Communication for Understanding Human Language Evolution: What's Missing?](https://mlsanity.com/paper/2204.10590/) (2022)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Dynamic population-based meta-learning for multi-agent communication with natural language](https://mlsanity.com/paper/2110.14241/) (2021)
- [Calibrate your listeners! Robust communication-based training for pragmatic speakers](https://mlsanity.com/paper/2110.05422/) (2021)
- [NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication](https://mlsanity.com/paper/2407.13999/) (2024)
- [The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication](https://mlsanity.com/paper/2407.17960/) (2024)
- [Language Evolution with Deep Learning](https://mlsanity.com/paper/2403.11958/) (2024)
- [Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocols](https://mlsanity.com/paper/2105.05069/) (2021)
- [A framework for the emergence and analysis of language in social learning agents](https://mlsanity.com/paper/2305.02632/) (2023)
- [Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agents](https://mlsanity.com/paper/2312.15985/) (2023)
- [Socially Supervised Representation Learning: the Role of Subjectivity in Learning Efficient Representations](https://mlsanity.com/paper/2109.09390/) (2021)
- [Modeling Human-Like Color Naming Behavior in Context](https://mlsanity.com/paper/2604.25674/) (2026)

## Abstract (arXiv)

Motivated by theories of language and communication that explain why communities with large numbers of speakers have, on average, simpler languages with more regularity, we cast the representation learning problem in terms of learning to communicate. Our starting point sees the traditional autoencoder setup as a single encoder with a fixed decoder partner that must learn to communicate. Generalizing from there, we introduce community-based autoencoders in which multiple encoders and decoders collectively learn representations by being randomly paired up on successive training iterations. We find that increasing community sizes reduce idiosyncrasies in the learned codes, resulting in representations that better encode concept categories and correlate with human feature norms.