Emergent Communication under Varying Sizes and Connectivities

Recent advances in deep neural networks allowed artificial agents to derive their own emergent languages that promote interaction, coordination, and collaboration within a group. Just as we humans have succeeded in creating a shared language that allows us to interact within a large group, can the emergent communication within an artificial group converge to a shared, agreed language? This research provides an analytical study of the shared emergent language within the group communication settings of different sizes and connectivities. As the group size increases up to hundreds, agents start to speak dissimilar languages, but the rate at which they successfully communicate is maintained. Remarkably, we also show an evidence of the shared language becoming more generalizable at describing new referents with increased group size. We observe the emergence of different dialects when we restrict the group communication to have local connectivities only. Finally, we provide an optimization result of group communication graphs when the number of agents one can communicate with is restricted.