# Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scale

arXiv: https://arxiv.org/abs/2401.08461 · HTML: https://mlsanity.com/paper/2401.08461/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 128 references that are in the map.
- First posted on arXiv 16 Jan 2024.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [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)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [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)
- [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)
- [Emergent Communication through Negotiation](https://mlsanity.com/paper/1804.03980/) (2018)
- [Learning Language Games through Interaction](https://mlsanity.com/paper/1606.02447/) (2016)
- [EGG: a toolkit for research on Emergence of lanGuage in Games](https://mlsanity.com/paper/1907.00852/) (2019)
- [Emergent Linguistic Phenomena in Multi-Agent Communication Games](https://mlsanity.com/paper/1901.08706/) (2019)
- [Compositional Obverter Communication Learning From Raw Visual Input](https://mlsanity.com/paper/1804.02341/) (2018)
- [Interpretable agent communication from scratch (with a generic visual processor emerging on the side)](https://mlsanity.com/paper/2106.04258/) (2021)
- [On the role of population heterogeneity in emergent communication](https://mlsanity.com/paper/2204.12982/) (2022)
- [Emergent Communication under Competition](https://mlsanity.com/paper/2101.10276/) (2021)
- [The Emergence of the Shape Bias Results from Communicative Efficiency](https://mlsanity.com/paper/2109.06232/) (2021)
- [Referential communication in heterogeneous communities of pre-trained visual deep networks](https://mlsanity.com/paper/2302.08913/) (2023)
- [Emergence of hierarchical reference systems in multi-agent communication](https://mlsanity.com/paper/2203.13176/) (2022)
- [A Practical Guide to Studying Emergent Communication through Grounded Language Games](https://mlsanity.com/paper/2004.09218/) (2020)
- [Context-dependent communication under environmental constraints](https://mlsanity.com/paper/2305.05821/) (2023)
- [Referential Uncertainty and Word Learning in High-dimensional, Continuous Meaning Spaces](https://mlsanity.com/paper/1609.09580/) (2016)

## Abstract (arXiv)

This paper introduces a general methodology through which a population of autonomous agents can converge on a linguistic convention that enables them to refer to arbitrary entities in their environment. The linguistic convention emerges in a decentralised manner through local communicative interactions between pairs of agents drawn from the population. The emergent convention consists of associations between symbolic labels (word forms) and subsymbolic concept representations (word meanings) that are grounded in a continuous feature space. We confirm the generality and scalability of the method through its evaluation on a wide and diverse selection of 37 publicly available datasets. Through a range of experiments, we demonstrate the robustness of the method against perceptual variation, including in heteromorphic populations, as well as the ability of the emergent conventions to self-adapt to changes in the environment.