# Visual Referential Games Further the Emergence of Disentangled Representations

arXiv: https://arxiv.org/abs/2304.14511 · HTML: https://mlsanity.com/paper/2304.14511/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 82 references that are in the map.
- First posted on arXiv 27 Apr 2023.

## Builds on (most cited first, 30 of 40)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [DARLA: Improving Zero-Shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/1707.08475/) (2017)
- [Language as an Abstraction for Hierarchical Deep Reinforcement Learning](https://mlsanity.com/paper/1906.07343/) (2019)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [A Benchmark for Systematic Generalization in Grounded Language Understanding](https://mlsanity.com/paper/2003.05161/) (2020)
- [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)
- [Learning Deep Disentangled Embeddings with the F-Statistic Loss](https://mlsanity.com/paper/1802.05312/) (2018)
- [Grounded Language Learning in a Simulated 3D World](https://mlsanity.com/paper/1706.06551/) (2017)
- [Are Disentangled Representations Helpful for Abstract Visual Reasoning?](https://mlsanity.com/paper/1905.12506/) (2019)
- [Compositional generalization through meta sequence-to-sequence learning](https://mlsanity.com/paper/1906.05381/) (2019)
- [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)
- [Ease-of-Teaching and Language Structure from Emergent Communication](https://mlsanity.com/paper/1906.02403/) (2019)
- [Anti-efficient encoding in emergent communication](https://mlsanity.com/paper/1905.12561/) (2019)
- [Linguistic generalization and compositionality in modern artificial neural networks](https://mlsanity.com/paper/1904.00157/) (2019)
- [Compositional generalization in a deep seq2seq model by separating syntax and semantics](https://mlsanity.com/paper/1904.09708/) (2019)
- [A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation](https://mlsanity.com/paper/2010.14766/) (2020)
- [Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks](https://mlsanity.com/paper/1807.07545/) (2018)
- [Environmental drivers of systematicity and generalization in a situated agent](https://mlsanity.com/paper/1910.00571/) (2019)
- [SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python](https://mlsanity.com/paper/1907.10121/) (2019)

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

- [Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play](https://mlsanity.com/paper/2509.25541/) (2025)
- [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)
- [Semantics and Spatiality of Emergent Communication](https://mlsanity.com/paper/2411.10173/) (2024)
- [ETHER: Aligning Emergent Communication for Hindsight Experience Replay](https://mlsanity.com/paper/2307.15494/) (2023)

## Abstract (arXiv)

Natural languages are powerful tools wielded by human beings to communicate information. Among their desirable properties, compositionality has been the main focus in the context of referential games and variants, as it promises to enable greater systematicity to the agents which would wield it. The concept of disentanglement has been shown to be of paramount importance to learned representations that generalise well in deep learning, and is thought to be a necessary condition to enable systematicity. Thus, this paper investigates how do compositionality at the level of the emerging languages, disentanglement at the level of the learned representations, and systematicity relate to each other in the context of visual referential games. Firstly, we find that visual referential games that are based on the Obverter architecture outperforms state-of-the-art unsupervised learning approach in terms of many major disentanglement metrics. Secondly, we expand the previously proposed Positional Disentanglement (PosDis) metric for compositionality to (re-)incorporate some concerns pertaining to informativeness and completeness features found in the Mutual Information Gap (MIG) disentanglement metric it stems from. This extension allows for further discrimination between the different kind of compositional languages that emerge in the context of Obverter-based referential games, in a way that neither the referential game accuracy nor previous metrics were able to capture. Finally we investigate whether the resulting (emergent) systematicity, as measured by zero-shot compositional learning tests, correlates with any of the disentanglement and compositionality metrics proposed so far. Throughout the training process, statically significant correlation coefficients can be found both positive and negative depending on the moment of the measure.