A Combinatorial Approach to Neural Emergent Communication
Not on the map. Why?
Abstract (arXiv)
Substantial research on deep learning-based emergent communication uses the referential game framework, specifically the Lewis signaling game, however we argue that successful communication in this game typically only need one or two symbols for target image classification because of a sampling pitfall in the training data. To address this issue, we provide a theoretical analysis and introduce a combinatorial algorithm SolveMinSym (SMS) to solve the symbolic complexity for classification, which is the minimum number of symbols in the message for successful communication. We use the SMS algorithm to create datasets with different symbolic complexity to empirically show that data with higher symbolic complexity increases the number of effective symbols in the emergent language.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 53 references that are in the map. First posted on arXiv 24 Oct 2024.
Builds on
18 of 53 references.
References · 18
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
- 2016Learning Multiagent Communication with Backpropagationcited by 366
- 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
- 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
- 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 185
- 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 125
- 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
- 2019Ease-of-Teaching and Language Structure from Emergent Communicationcited by 65
- 2018How agents see things: On visual representations in an emergent language gamecited by 45
- 2019EGG: a toolkit for research on Emergence of lanGuage in Gamescited by 42
6 more
- 2021Emergent Communication of Generalizationscited by 42
- 2019Emergence of Compositional Language with Deep Generational Transmissioncited by 17
- 2019Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordancescited by 11
- 2023EC^2: Emergent Communication for Embodied Controlcited by 10
- 2021Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocolscited by 2
- 2020Intrinsically Motivated Compositional Language Emergencecited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.