On The Plurality of Graphs

TL;DR

This paper empirically investigates how different graph structures and centrality-based edge sampling influence language emergence in multi-agent communication games, highlighting the importance of network topology.

Contribution

It demonstrates experimentally that the graph generation process and edge sampling centrality significantly affect language emergence dynamics.

Findings

Graph structure impacts communication outcomes

Centrality measures influence language development

Network topology plays a crucial role in emergent communication

Abstract

We conduct a series of experiments designed to empirically demonstrate the effects of varying the structural features of a multi-agent emergent communication game framework. Specifically, we model the interactions (edges) between individual agents (nodes)as the structure of a graph generated according to a series of known random graph generating algorithms. Confirming the hypothesis proposed in [10], we show that the two factors of variation induced in this work, namely 1) the graph-generating process and 2) the centrality measure according to which edges are sampled, in fact play a significant role in determining the dynamics of language emergence within the population at hand.