Emergent Communication for Co-constructed Emotion Between Embodied Agents via Collective Predictive Coding
Zehang Zhang, Nguyen Le Hoang, Tadahiro Taniguchi, Takato Horii

TL;DR
This paper models emergent communication between embodied agents to understand how shared emotional understanding develops, demonstrating that communication enhances alignment of emotion categories even with divergent interoceptive signals.
Contribution
It introduces a novel computational framework combining Collective Predictive Coding and the Metropolis-Hastings Naming Game to simulate social emotion co-construction.
Findings
Communication improves emotion category alignment and clarity.
Alignment is concentrated at the symbolic layer rather than perceptual representations.
Robust categorical alignment occurs despite divergent interoceptive dynamics.
Abstract
According to the theory of constructed emotion, the brain actively forms emotion categories by integrating multimodal bodily signals, and constructs emotional experiences by using these categories to predict and interpret sensory inputs. While research has advanced in modeling individual emotion construction, the social process of co-construction-how a shared understanding of emotions emerges between individuals-remains computationally underexplored. This study investigates this process by modeling emergent communication between two embodied agents using the Metropolis-Hastings Naming Game (MHNG), grounded in the Collective Predictive Coding (CPC) framework. Our experiments, using visual, auditory, and simulated interoceptive inputs, yield two main findings. First, MHNG-based communication significantly improves the alignment, clarity, and inter-agent agreement of the learned emotion…
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.
