Semantics and Spatiality of Emergent Communication

TL;DR

This paper investigates the semantics of emergent communication in artificial agents, showing that reconstruction objectives promote meaningful and spatially consistent messages, unlike discrimination objectives.

Contribution

It introduces the concept of semantic consistency, provides a formal comparison of discrimination and reconstruction objectives, and validates findings through experiments.

Findings

Reconstruction encourages semantic consistency in communication.

Discrimination can lead to semantically inconsistent protocols.

Distance-based goals promote spatial meaningfulness.

Abstract

When artificial agents are jointly trained to perform collaborative tasks using a communication channel, they develop opaque goal-oriented communication protocols. Good task performance is often considered sufficient evidence that meaningful communication is taking place, but existing empirical results show that communication strategies induced by common objectives can be counterintuitive whilst solving the task nearly perfectly. In this work, we identify a goal-agnostic prerequisite to meaningful communication, which we term semantic consistency, based on the idea that messages should have similar meanings across instances. We provide a formal definition for this idea, and use it to compare the two most common objectives in the field of emergent communication: discrimination and reconstruction. We prove, under mild assumptions, that semantically inconsistent communication protocols can be optimal solutions to the discrimination task, but not to reconstruction. We further show that the reconstruction objective encourages a stricter property, spatial meaningfulness, which also accounts for the distance between messages. Experiments with emergent communication games validate our theoretical results. These findings demonstrate an inherent advantage of distance-based communication goals, and contextualize previous empirical discoveries.