Emergent Graphical Conventions in a Visual Communication Game
Shuwen Qiu, Sirui Xie, Lifeng Fan, Tao Gao, Jungseock Joo, Song-Chun, Zhu, Yixin Zhu

TL;DR
This paper models how graphical conventions emerge in visual communication through neural agents, revealing insights into the evolution of sketches that balance iconicity and symbolicity, and demonstrating adaptive communication strategies.
Contribution
It introduces a novel reinforcement learning framework for simulating emergent graphical conventions in neural agents during a visual communication game.
Findings
Evolved sketches preserve semantic continuity under environmental pressures.
Agents can switch between conventionalized and iconic communication based on familiarity.
Experimental results align with human studies of graphical conventions.
Abstract
Humans communicate with graphical sketches apart from symbolic languages. Primarily focusing on the latter, recent studies of emergent communication overlook the sketches; they do not account for the evolution process through which symbolic sign systems emerge in the trade-off between iconicity and symbolicity. In this work, we take the very first step to model and simulate this process via two neural agents playing a visual communication game; the sender communicates with the receiver by sketching on a canvas. We devise a novel reinforcement learning method such that agents are evolved jointly towards successful communication and abstract graphical conventions. To inspect the emerged conventions, we define three fundamental properties -- iconicity, symbolicity, and semanticity -- and design evaluation methods accordingly. Our experimental results under different controls are consistent…
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
Taxonomy
TopicsAesthetic Perception and Analysis · Artificial Intelligence in Games · Music and Audio Processing
