# Structural Inductive Biases in Emergent Communication

arXiv: https://arxiv.org/abs/2002.01335 · HTML: https://mlsanity.com/paper/2002.01335/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2020.

## Built on by (most cited first, 5 of 5)

- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs](https://mlsanity.com/paper/2602.11583/) (2026)
- [Emergent Communication with Attention](https://mlsanity.com/paper/2305.10920/) (2023)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)
- [SimSiam Naming Game: A Unified Approach for Emergent Communication and Representation Learning](https://mlsanity.com/paper/2410.21803/) (2024)

## Abstract (arXiv)

In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence. We investigate the impact of representation learning in artificial agents by developing graph referential games. We empirically show that agents parametrized by graph neural networks develop a more compositional language compared to bag-of-words and sequence models, which allows them to systematically generalize to new combinations of familiar features.