Towards Graph Representation Learning in Emergent Communication
This addresses the challenge of developing effective communication protocols for multi-agent AI systems, though it appears incremental as it builds on existing referential game frameworks with graph-based adaptations.
The paper tackles the problem of language emergence and cooperation in multi-agent systems by proposing a graph referential game with varying complexity, using graph convolutional networks. The result shows that the emerged communication protocol is robust, agents uncover true factors of variation, and they generalize beyond training samples.
Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces). In order to communicate, we flatten the complex representation of entities and their attributes into a single word or a sentence. In this paper we use graph convolutional networks to support the evolution of language and cooperation in multi-agent systems. Motivated by an image-based referential game, we propose a graph referential game with varying degrees of complexity, and we provide strong baseline models that exhibit desirable properties in terms of language emergence and cooperation. We show that the emerged communication protocol is robust, that the agents uncover the true factors of variation in the game, and that they learn to generalize beyond the samples encountered during training.