A Compressive-Expressive Communication Framework for Compositional Representations

TL;DR

This paper introduces CELEBI, a novel self-supervised framework that enhances the emergence of compositional, efficient, and expressive communication protocols in neural agents through a combination of innovative mechanisms, improving over prior methods.

Contribution

The paper presents CELEBI, integrating three mechanisms to promote compressibility, expressivity, and efficiency in emergent language, advancing the understanding of structured communication in neural models.

Findings

Improved reconstruction accuracy on Shapes3D and MPI3D datasets.

Enhanced topographic similarity indicating better compositionality.

Surpassed prior discrete communication frameworks in efficiency and structure.

Abstract

Compositionality in knowledge and language--the ability to represent complex concepts as a combination of simpler ones--is a hallmark of human cognition and communication. Despite recent advances, deep neural networks still struggle to acquire this property reliably. Neural models for emergent communication look to endow artificial agents with compositional language by simulating the pressures that form human language. In this work, we introduce CELEBI (Compressive-Expressive Language Emergence through a discrete Bottleneck and Iterated learning), a novel self-supervised framework for inducing compositional representations through a reconstruction-based communication game between a sender and a receiver. Building on theories of language emergence and the iterated learning framework, we integrate three mechanisms that jointly promote compressibility, expressivity, and efficiency in the emergent language. First, Progressive Decoding incentivizes intermediate reasoning by requiring the receiver to produce partial reconstructions after each symbol. Second, Final-State Imitation trains successive generations of agents to imitate reconstructions rather than messages, enforcing a tighter communication bottleneck. Third, Pairwise Distance Maximization regularizes message diversity by encouraging high distances between messages, with formal links to entropy maximization. Our method significantly improves both the efficiency and compositionality of the learned messages on the Shapes3D and MPI3D datasets, surpassing prior discrete communication frameworks in both reconstruction accuracy and topographic similarity. This work provides new theoretical and empirical evidence for the emergence of structured, generalizable communication protocols from simplicity-based inductive biases.