Compositional Understanding in Signaling Games
David Peter Wallis Freeborn

TL;DR
This paper introduces new signaling game models that enable receivers to develop genuine compositional understanding by learning from atomic message components, overcoming limitations of previous models.
Contribution
It presents two simplified models, a minimalist and a generalist, that facilitate the evolution of compositional understanding in signaling games.
Findings
Receivers can learn from atomic message components in the new models.
Models are simpler than previous approaches, enabling better compositional understanding.
Genuine compositional understanding evolves in the proposed signaling game models.
Abstract
Receivers in standard signaling game models struggle with learning compositional information. Even when the signalers send compositional messages, the receivers do not interpret them compositionally. When information from one message component is lost or forgotten, the information from other components is also erased. In this paper I construct signaling game models in which genuine compositional understanding evolves. I present two new models: a minimalist receiver who only learns from the atomic messages of a signal, and a generalist receiver who learns from all of the available information. These models are in many ways simpler than previous alternatives, and allow the receivers to learn from the atomic components of messages.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
