Visualizing Coalition Formation: From Hedonic Games to Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: França, Pedro Henrique de Paula, Felipe, Lucas Lopes, Menasché, Daniel Sadoc
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910046070243328
author França, Pedro Henrique de Paula
Felipe, Lucas Lopes
Menasché, Daniel Sadoc
author_facet França, Pedro Henrique de Paula
Felipe, Lucas Lopes
Menasché, Daniel Sadoc
contents We propose image segmentation as a visual diagnostic testbed for coalition formation in hedonic games. Modeling pixels as agents on a graph, we study how a granularization parameter shapes equilibrium fragmentation and boundary structure. On the Weizmann single-object benchmark, we relate multi-coalition equilibria to binary protocols by measuring whether the converged coalitions overlap with a foreground ground-truth. We observe transitions from cohesive to fragmented yet recoverable equilibria, and finally to intrinsic failure under excessive fragmentation. Our core contribution links multi-agent systems with image segmentation by quantifying the impact of mechanism design parameters on equilibrium structures.
format Preprint
id arxiv_https___arxiv_org_abs_2603_07890
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Visualizing Coalition Formation: From Hedonic Games to Image Segmentation
França, Pedro Henrique de Paula
Felipe, Lucas Lopes
Menasché, Daniel Sadoc
Artificial Intelligence
Computer Vision and Pattern Recognition
91A43
I.2.11; I.4.6
We propose image segmentation as a visual diagnostic testbed for coalition formation in hedonic games. Modeling pixels as agents on a graph, we study how a granularization parameter shapes equilibrium fragmentation and boundary structure. On the Weizmann single-object benchmark, we relate multi-coalition equilibria to binary protocols by measuring whether the converged coalitions overlap with a foreground ground-truth. We observe transitions from cohesive to fragmented yet recoverable equilibria, and finally to intrinsic failure under excessive fragmentation. Our core contribution links multi-agent systems with image segmentation by quantifying the impact of mechanism design parameters on equilibrium structures.
title Visualizing Coalition Formation: From Hedonic Games to Image Segmentation
topic Artificial Intelligence
Computer Vision and Pattern Recognition
91A43
I.2.11; I.4.6
url https://arxiv.org/abs/2603.07890