# CtD: Composition through Decomposition in Emergent Communication

arXiv: https://arxiv.org/abs/2601.10169 · HTML: https://mlsanity.com/paper/2601.10169/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 86 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (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)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [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)
- [Measuring Compositionality in Representation Learning](https://mlsanity.com/paper/1902.07181/) (2019)
- [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)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [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)
- [The paradox of the compositionality of natural language: a neural machine translation case study](https://mlsanity.com/paper/2108.05885/) (2021)
- [Online Clustered Codebook](https://mlsanity.com/paper/2307.15139/) (2023)
- [Codebook Features: Sparse and Discrete Interpretability for Neural Networks](https://mlsanity.com/paper/2310.17230/) (2023)

## Built on by (most cited first, 1 of 1)

- [Investigating the Development of Task-Oriented Communication in Vision-Language Models](https://mlsanity.com/paper/2601.20641/) (2026)

## Abstract (arXiv)

Compositionality is a cognitive mechanism that allows humans to systematically combine known concepts in novel ways. This study demonstrates how artificial neural agents acquire and utilize compositional generalization to describe previously unseen images. Our method, termed "Composition through Decomposition", involves two sequential training steps. In the 'Decompose' step, the agents learn to decompose an image into basic concepts using a codebook acquired during interaction in a multi-target coordination game. Subsequently, in the 'Compose' step, the agents employ this codebook to describe novel images by composing basic concepts into complex phrases. Remarkably, we observe cases where generalization in the `Compose' step is achieved zero-shot, without the need for additional training.