SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication

TL;DR

This paper introduces SSNG, a novel feedback-free emergent communication framework that uses self-supervised representation alignment and Gumbel-Softmax relaxation to improve multi-agent symbolic communication.

Contribution

SSNG replaces sampling-based updates with a symmetric self-supervised alignment objective, enabling efficient, gradient-based emergent communication without explicit feedback.

Findings

SSNG achieves higher classification accuracy than referential and reconstruction games.

Emergent messages from SSNG outperform those from MHNG in experiments.

Self-supervised alignment effectively facilitates feedback-free emergent communication.

Abstract

Emergent Communication (EmCom) investigates how agents develop symbolic communication through interaction without predefined language. Recent frameworks, such as the Metropolis--Hastings Naming Game (MHNG), formulate EmCom as the learning of shared external representations negotiated through interaction under joint attention, without explicit success or reward feedback. However, MHNG relies on sampling-based updates that suffer from high rejection rates in high-dimensional perceptual spaces, making the learning process sample-inefficient for complex visual datasets. In this work, we propose the SimSiam Naming Game (SSNG), a feedback-free EmCom framework that replaces sampling-based updates with a symmetric, self-supervised representation alignment objective between autonomous agents. Building on a variational inference--based probabilistic interpretation of self-supervised learning, SSNG formulates symbol emergence as an alignment process between agents' latent representations mediated by message exchange. To enable end-to-end gradient-based optimization, discrete symbolic messages are learned via a Gumbel--Softmax relaxation, preserving the discrete nature of communication while maintaining differentiability. Experiments on CIFAR-10 and ImageNet-100 show that the emergent messages learned by SSNG achieve substantially higher linear-probe classification accuracy than those produced by referential games, reconstruction games, and MHNG. These results indicate that self-supervised representation alignment provides an effective mechanism for feedback-free EmCom in multi-agent systems.