CtD: Composition through Decomposition in Emergent Communication

Boaz Carmeli, Ron Meir, Yonatan Belinkov

Keywords: Emergent communication, Compositionality, Codebook learning

TL;DR: This work demonstrates that discretizing the latent space and communication channel with a discrete codebook significantly enhances compositional generation in emergent communication.

Abstract:

Compositionality is a cognitive mechanism that allows humans to systematically combine known concepts in novel ways.
This study demonstrates how artificial neural agents acquire and utilize compositional generalization to describe previously unseen images.
Our method, termed \`\`Composition through Decomposition'', involves two sequential training steps.
In the \'Decompose\' step, the agents learn to decompose an image into basic concepts using a codebook acquired during interaction in a multi-target coordination game.
Subsequently, in the \`Compose\' step, the agents employ this codebook to describe novel images by composing basic concepts into complex phrases.
Remarkably, we observe cases where generalization in the `Compose' step is achieved zero-shot, without the need for additional training.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3547